AI revolutionizes the supply chain

Nuremberg public transport: Real-time-capable algorithms act as driver assistance system controlling subways

One example is the driver and track control system in the Nuremberg subway. On some days, two subway lines not only travel automatically, but can also be optimized to save energy. So when a subway train sweeps into the station and stops at the platform with a gentle hiss, most commuters have no idea that it perhaps braked three seconds earlier than usual. But these few seconds can reduce the operator’s energy costs by an impressive amount. The driver assistance system develops an optimal timetable, searches for energy-efficient speed profiles, uses coasting phases and avoids too many simultaneous departures, which generate high and expensive load peaks. It was developed at the ADA Lovelace Center for Analytics, Data and Applications. This is where Fraunhofer IIS, under the project management of the Center for Applied Research on Supply Chain Services, collaborates with FAU Erlangen-Nürnberg, LMU Munich, Fraunhofer IKS and Fraunhofer IISB on research into subjects such as the mathematical foundations of artificial intelligence in order to develop powerful new techniques and bring them to practical maturity in industrial collaborations.

Schnellecke: Complex and dynamic warehousing

Another organization that needs optimal timetabling is the Schnellecke Group, although in its case inside a warehouse. The service provider based in Leipzig picks and delivers items directly to automotive production lines according to tight schedules. Every day, dozens or even hundreds of trucks deliver goods in boxes, which have to be stored in warehouses. “Schnellecke has regularly encountered major challenges in the warehousing of goods. Even brief delays disrupted the process flow. Where’s the best place to store the boxes? Maybe it’s not such a good idea to put urgent items in the farthest-flung corner? And window handles and glass panels should ideally be stored together,” says Menden. Our algorithm not only makes optimal use of the space, but also takes into account health and safety and short driving and walking distances. As a solution, we developed a mixed-integer optimization model, which breaks problems down successively into ever smaller subproblems using exact optimization algorithms and then solves them with simpler methods.

Magna Seating: Car seats – lack of data for troubleshooting

We find another AI success story with the automotive supplier Magna Seating, which manufactures car seats. Every now and again, a seat has a little fault that needs to be rectified. The checks are time-consuming, and the faulty parts jeopardize deadline commitments. By selecting and applying suitable statistical techniques, we enabled our customer to identify regularities in fault incidents and take appropriate countermeasures. Although these faults are rare, this very scarcity makes analyzing them a challenge. Employing conventional statistical methods for the analysis, Menden’s team identify precisely the events that correlate with the fault, paving the way for higher product quality with less rework. And AI is even able to determine the optimum sequence in which the seats should be loaded into the delivery truck.

Tea manufacturing: Blends of raw materials with variable qualities

Avoiding production errors is not the issue at the Martin Bauer Group; rather, it is how to manufacture products of consistent quality using raw materials with varying properties. The group produces herbal and fruit tea blends for supermarkets and drugstores. As the ingredients of the botanical raw materials vary, warehouse and production planning are very time-intensive operations at the Martin Bauer Group. We solved this pooling problem for tea blends with optimization software that takes into account stock levels, storage periods, laboratory analytics, intermediate and end products, and the various quality requirements of customers. With the solution jointly developed by researchers from our working group and FAU Erlangen-Nürnberg, the dispatchers are able to quickly run through various scenarios, which otherwise would have too many combinations to be solved by humans alone. This kind of problem is not limited to tea manufacturing either, but also arises in many other areas of the food industry and in industrial manufacturing.

OBER: Optimal inventory planning quantifies uncertainties of forecasts

“Out of stock” has been an oft-heard refrain in recent times. Wood, bathroom fittings, canned vegetables and toilet paper are not in stock when customers come in to buy them. At the same time, goods that are not in demand are taking up valuable space. Before now, businesses have usually relied on very simple forecasts based on average sales to date, even though these predictions are riddled with uncertainties. In the OBER research project, we combine forecasts specially designed for the wholesale sector with mathematical optimization, taking into account restrictions such as the best price, available storage space and financial resources. Moreover, the AI we developed quantifies the uncertainty of the prediction. It calculates the optimum strategic course of action even for goods that will not be ordered for a few months.

AutoML – automatic selection of the best model at any given moment

Finding the most suitable mathematical procedure for any given application is time-consuming. For a solution, we looked to AutoML (automated machine learning). We use an umbrella model that automatically analyzes the various algorithms and independently selects the most suitable model. With Online AutoML, moreover, it is possible to continuously review whether the model currently being used is still the best one. Because when production suddenly changes the recipe for gingerbread or if a different car model is to be manufactured, then another machine learning algorithm might be better suited to the new task. AutoML is therefore versatile and can be used in many domains, as its abstraction at the mathematical level works for many applications.