Monitoring and Scheduling of Semiconductor Failure Analysis Labs

Identifying and locating non-conformities, such as physical failures causing electrical malfunctioning of a device, in modern semiconductor devices is a challenging task. Typically, highly qualified employees in a failure analysis (FA) lab use sophisticated and expensive tools like scanning electron microscopes to identify and locate such non-conformities. Given the increasing complexity of investigated devices and very limited resources, labs may struggle to deliver analysis results in time. This paper suggests an approach to optimize the usage of FA lab resources by adaptive scheduling and monitoring. In particular, we combine constraints programming for the computation of a schedule with stream reasoning to monitor the lab's conditions and maintain the schedule depending on the situation. Evaluation results indicate that our system can significantly improve the tardiness of a real-world FA lab, and all its computational tasks can be finished in an average time of 3.6 seconds, with a maximum of 15.2 seconds, which is acceptable for the lab's workflows.