Event Alignment, Warping between Running Speeds

We are pursuing a system that monitors the engine condition under multiple load settings, i.e. under non-stationary operating conditions. We have obtained data from the electronically controlled 2-stroke engine at MAN B&W Research Copenhagen. The running speed when data acquired under simulated marine conditions (different load settings on the propeller curve) was in the range from 60 to 120 rotations per minute; furthermore the running speed was stable within periods of fixed load. Electronically controlled engines can change the angular timing of certain events, such as fuel injection in order to optimize its performance. However this behaviour inhibits our framework presented in COMADEM 2003 from detecting condition changes across those load changes. This paper evaluates different methods that align acoustic emission signals observed under different load settings. We evaluate the methods on data from the fuel injection period where the largest deviations in timing occur. The idea is that we, given aligned data, can use the already developed component analysis framework for non-stationary monitoring of condition changes. It should further be noticed that the proposed warp framework also enables alignment across cylinders and engines.