A Timed Automaton Model with Timing Intervals and Outputs for Fault Diagnosis of the Drilling Process on a CNC Machine

Fault diagnosis is a crucial task to guarantee reliability and reduce losses and production cost in smart machining in the Industry 4.0. In order to do so, it is necessary to implement a fault diagnoser that does not use a large amount of memory and which is capable of detecting the occurrence of a fault in a fast manner. In this paper, we propose a timed automaton model, called Timed Automaton with Timing Intervals and Outputs (TATIO), which is suitable for fault diagnosis. The TATIO model represents a typical drilling process on a CNC machine which uses an ISO code for programming and is obtained by identification of timing intervals associated with the time instants that the events occur in the system. The fault diagnoser uses only the spindle power and Z position read directly from the system controller and does not need any additional sensor. The proposed diagnoser is capable of detecting the use of a wrong cutting speed for a specific workpiece material, the use of a material different from the expected, and the occurrence of a wrong sequence of events executed by the system.