“…Based on measurement data, Principal Component Analysis (PCA) can be used to build a probabilistic model of variability from the empirical mean and covariance of surface deviations at different locations on the blade [22,23,24]. Following [25,26], we assume that the geometric variability in manufactured turbine blades can be accurately described as a non-stationary Gaussian Random Field e(s, ω), ω being a coordinate in the sample space Ω, and (Ω, F , P) a complete probability space. The arclength s ∈ [0, 1] parametrizes the location on the blade surface, starting at the trailing edge (s = 0), going around the leading edge (s = 1 2 ), and continuing back to the trailing edge on the opposite side of the blade (s = 1).…”