Multi-label learning using label-specific features for simultaneous fault diagnosis of aircraft engine

Lacking of the management of simultaneous fault is one of the limitations of condition monitoring for a gas turbine, which is critical for the safety and decision-making of aircraft operation. To this end, this paper employed a multi-label (ML) learning strategy to address the simultaneous fault issues. Moreover, a feature selection algorithm is proposed, which is based on the viewpoint that different class labels might be distinguished by certain specific characteristics of their own. The proposed algorithm achieves the goal of label-specific feature selection by iteratively optimizing the weight reconstruction matrix, and the learned label-specific features for the corresponding label can be used for multi-label classification. As thus, sensor data for different components of aircraft engines can be determined by the proposed algorithm to deal with the simultaneous fault diagnosis. Finally, comprehensive experiments on the benchmark data sets of multi-label learning validate the advantages and feasibility of the presented approaches, and the effectiveness of their application to simultaneous fault diagnosis of aircraft engines is also proved by extensive experiments.