Data sets from CPS for ML applications
The LiU-ICE benchmark covers some challenging problems of fault diagnosis of technical systems. A diagnosis system gives important information to the control system, to monitor the health of the system, and select suitable countermeasures against system degradation and faults but also to assist technicians at the workshop to reduce downtime. The diagnosis system needs to identify the faulty component as fast and accurately as possible. However, it is also important to avoid misclassifications and falsely rejecting the true diagnosis since this can result in increased costs and reduced trust in the diagnosis system.