Unforeseen machine tool failures due to technical issues can cause downtimes leading to delays during production. To reduce delays, rescheduling of the production is, in most cases, necessary. However, warranting such a change requires reliable knowledge about the duration of the failure. This article presents a method to provide this knowledge by estimating the duration of a machine tool failure based on previous failure durations. Using the cross-industry standard process for data mining (CRISP-DM) and statistical methods, the embedded model for failure classification and duration is continuously improved. The method is thoroughly tested using multiple distributions, parameters and a practical use case. The results show high potential for predicting the duration of machine tool failures, which consequently could lead to improved quality of rescheduling.

The maintenance and repair of jet or gas turbine components has a considerably high share in the overall turbine operating costs. The authors deal with the regeneration process of complex capital goods considering jet engines as an example, with turbine blades being the most important components to be regenerated. In order to decide on a reasonable and economical regeneration path, maintenance approaches typically require detailed knowledge of the shape and wear condition of the components. In order to select suitable repair strategies for each component, the best possible knowledge about geometry, damages and surface topologies is necessary. In order to meet these requirements, a novel combination of non-destructive testing and measuring methods will be presented. Each process can be adapted for inline operation. The presented methods also enable quality control of the regenerated components that have completed their individual regeneration path. Due to the high variety of possible defects on turbine blades, the individually presented methods can be combined to form an inspection sequence. Detailed status monitoring before and after maintenance becomes possible for each component. This provides the basis for further decisions in the regeneration process.