||Multivariate statistical tools based of principal component analysis (PCA) has been used since long in various manufacturing and process industries for process monitoring. In this study, PCA based fault propagation path estimation algorithm has been developed and applied on the liquefied natural gas (LNG) process. The developed methodology predicts the fault direction by projecting the samples on the residual subspace (RS). The RS of fault data is usually superimposed by normal variations which must be eliminated to amplify the fault magnitude. Therefore, the fault amplification methodology is used to minimize the normal process variations to maximize the fault affect in the RS. The RS is further converted into co-variance matrix and singular value decomposition (SVD) is applied to the co-variance structure to generate the fault direction matrix corresponding to the eigenvalues. The process variables are further arranged in their hierarchical order according to their contribution to estimate the fault propagation path in the system. Additionally, the developed algorithm also detects the origin of the fault irrespective of using the fault detection indices.