FFD-Clustering: An unsupervised anomaly detection method for aero-engines based on fuzzy fusion of variables and discriminative mapping of features

The original monitoring data from aero-engines possess characteristics such as high dimensionality, strong noise, and imbalance, which present substantial challenges to traditional anomaly detection methods. In response, this paper proposes a method based on Fuzzy Fusion of variables and Discriminant mapping of features for Clustering (FFD-Clustering) to detect anomalies in original monitoring data from Aircraft Communication Addressing and Reporting System (ACARS). Firstly, associated variables are fuzzily grouped to extract the underlying distribution characteristics and trends from the data. Secondly, a multi-layer contrastive denoising-based feature Fusion Encoding Network (FEN) is designed for each variable group, which can construct representative features for each variable group through eliminating strong noise and complex interrelations between variables. Thirdly, a feature Discriminative Mapping Network (DMN) based on reconstruction difference re-clustering is designed, which can distinguish dissimilar feature vectors when mapping representative features to a unified feature space. Finally, the K-means clustering is used to detect the abnormal feature vectors in the unified feature space. Additionally, the algorithm is capable of reconstructing identified abnormal vectors, thereby locating the abnormal variable groups. The performance of this algorithm was tested on two public datasets and real original monitoring data from four aero-engines’ ACARS, demonstrating its superiority and application potential in aero-engine anomaly detection.