Engineers in large companies often have to make decisions, which are auxiliary with respect to their main activities. For instance, detection and localization of faults is a primary task of an engineer in a fault analysis (FA) lab.

The throughput of the lab depends on how the engineers select the analyses to perform. An inappropriate order might result in violated deadlines or bottlenecks in the queues of the tools. As a result, additional costs might appear even. Deciding which job to pick next is quite complicated, because an engineer should consider factors like the availability of tools and materials for the current analysis and all subsequent ones required by the job. Moreover, the engineer should compare the job at hand with other jobs, which have higher priority, an approaching deadline, or stuck in a tool queue. All this data is available in the FA information systems, but the collection and analysis take time and thus, is not always used by experts. As a result, the lab engineers select jobs in a non-optimal ad hoc manner.

The goal of the LotTravelerAI PhD project is to develop methods that help FA employees to organize their routines optimally. To reach this goal two main problems will be addressed:

• Monitoring – identify situations in a lab that might cause violation of the current schedule
• Scheduling – recommend job sequences to engineers that optimize the lab’s overall throughput using the data available in the existing information systems.

In this project, we will extend the state-of-the-art monitoring and scheduling techniques and develop new ones to meet the requirements of the suggested intelligent assisting system.

The LotTravelerAI project is funded by the Austrian Research Promotion Agency (FFG). By granting funds to a selection of innovative PhD-proposals, the FFG encourages additional cooperation between industrial research and universities in Austria.