The sensitivity of various features that are characteristics of machine performance may vary significantly under different working conditions. Thus it is critical to devise a systematic feature extraction (FE) approach that provides a useful and automatic guidance on using the most effective features for machine performance recognition without human intervention. This paper proposes a locality preserving projection (LPP)-based FE approach for machine performance degradation recognition. Different from principal component analysis (PCA) that aims to discover the global structure of the Euclidean space, LPP is capable to discover local structure of the data manifold. This may enable LPP to find more meaningful low-dimensional information hidden in the high-dimensional observations compared with PCA. This experimental result on a bearing test-bed shows that LPP-based FE improves the performance of recognizers for identifying performance degradation of bearings.