Ideas / Shapes in series
ExperimentFaults in sensor history
Can slow faults be seen in unevenly recorded sensor data before an alarm?
Years of unevenly recorded sensor readings read by shape, to see slow faults before an alarm limit is reached. A benchmark on public data, written up.
Research
How the historian benchmark is built
A pre-registered benchmark that scores fault detectors on data kept the way a process historian keeps it, from public fault datasets through a simulated historian, four ways of reading the archive and a shared false-alert budget to decision rules frozen before scoring.
Watching historian data by its shape
Utilities already record years of readings from every transformer, pump and meter. We are testing whether reading that record by its shape rather than its value can warn of some slow faults sooner than an alarm limit does, recognise a fault from other assets in the fleet, and say what is likely to happen next.