In this paper, the use of Linear and Kernel PCA for fault isolation and prognosis is explored since PCA is normally utilized for detection and isolation. Vector projection and statistical analysis were utilized to isolate and predict faults in the PCA domain. Linear PCA was applied to data collected from experiments on a one half horsepower centrifugal water pump both for normal and faulty operation consisting of the four fault scenarios: impeller failure, seal failure, inlet pressure sensor failure, and a filter clog. Upon close observation of the behavior of the principal component scores, it was determined that the linear PCA does not adequately isolate and predict the failures. Therefore, Kernel PCA, utilizing a Gaussian kernel, was applied to the same data sets. Analysis of the behavior shows that the principal component scores gained from the Kernel PCA performed better than linear PCA.