Fast Quench Detection in SFCL Pancake Using Optical Fibre Sensing and Machine Learning

A fast hotspot detection technique has been implemented and patented at École Polytechnique Fédérale de Lausanne (EPFL) under the European Union project FastGrid. The optical fibre sensing based uses Mach-Zehnder Interferometer (MZI) can detect even singular hotspots in superconductor within 15ms. MZI setup is very sensitive to external perturbations mechanical stresses, which manifest output along with response hotspots. disturbance subject to, varies sample being tested environment it in. For example, length configuration, addition routing of determine extent stresses on fibre. Previous publications, showcased experiment results relatively simple configurations were straight HTS tapes short lengths (0.3m or 1m). This manuscript will investigate feasibility for a more complicated type: pancake prototype superconducting fault current limiter (SFCL), comprising 12m tape bifilar winding, taped conductor. also give brief overview machine learning post processing experimental data, developed EPFL supplement quench easy reliable large scale applications.