Development of a digital twin towards enhanced monitoring of the SF6 subsystem on the Z Machine

In this work, we develop a digital twin (DTW) of the Sulfur Hexafluoride (SF6) subsystem on the Z Machine at Sandia National Laboratories. The Z Machine is a premier pulsed power research facility for studying high energy density science, to which SF6 serves as an insulating gas. A DTW can dynamically update alongside its physical counterpart using real-time data, providing a precise estimate of the system’s internal state which can augment monitoring processes. Thus, partially motivating the development of this DTW is a desire for online leak detection, as SF6 emissions are regulated and reportable. The DTW discussed in this work supports real-time, online IO and interaction with the SF6 control system; it has been incorporated as the plant model in a state observer, using online telemetry to synchronize the DTW’s state with that of the physical system in a software in the loop framework. We discuss future enhancements to the digital twin aimed at minimizing SF6 loss, including leak detection, leak localization, and leak isolation algorithms, as well as potential predictive maintenance strategies.