Mixed-kernel Slow Feature Analysis Based Feature Extraction on Civil Aero-engine gas path parameters

A mixed-kernel Slow Feature Analysis (MKSFA) based feature extraction on civil aero-engine gas path parameters is proposed to extract the slowest time-varying features of gas path parameters on civil aero-engine. By introducing the mixed-kernel function in Slow Feature Analysis, the original input data can be fully expanded into a high-dimensional feature space while avoiding the computational difficulties caused by the high-dimensional feature space. The result of MKSFA is compared with the traditional feature extraction of principal component analysis and auto-encoder to verify the reliability of this algorithm, which proves that the feature extraction method proposed in this paper is more suitable for the anomaly detection field of aero-engine gas path parameters.