Patent attributes
A method of analysing measured data from a system having multiple associated system variables, the method including the steps of: a) optimizing an error function relating the measured data to a predetermined number of the system variables to adjust the system variables; b) selecting a subset of the adjusted variables; and c) re-optimizing the error function by adjusting only the variables in the subset. A method of identifying likely contributors to an error caused in measured data from a system which has multiple associated system variables. A method of analysing measured engine service or test data form an engine having a plurality of associated system variables, includes the step of optimizing an error function which relates the measured data to a predetermined number of the system variables, by least-absolutes optimization wherein the error function is a sum of absolute variations.
