Siamese multiscale residual feature fusion network for aero-engine bearing fault diagnosis under small-sample condition

Abstract

Implementing condition monitoring and fault diagnosis of aero-engine bearing is crucial for ensuring aircraft operate safely and reliably. In engineering practice, the fault data for aero-engine bearings is extremely limited. However, the traditional fault diagnosis methods have two shortcomings under extremely small sample conditions: (1) they have limited diagnostic performance and generalization ability; (2) they do not mine fault information sufficiently and efficiently. This article proposes a siamese multiscale residual feature fusion network (SMSRFFN) for aero-engine bearings fault diagnosis under small sample conditions to overcome the weaknesses above. In the proposed SMSRFFN, the training samples are first paired in pairs according to the matching rules to realize the expansion of the sample size. Secondly, a multiscale residual feature extraction network (MSRFEN) is constructed to excavate the fault features of different scales and speed up the convergence speed of the network. Then, a multiscale attention mechanism feature fusion module (MSAMFFM) is designed to achieve efficient fusion of fault features at different scales. Finally, the distance of the input sample is measured based on the fused deep feature representation to identify the fault state of the aero-engine bearing. The proposed SMSRFFN is evaluated using three bearing fault data and also compared with some state-of-the-art small sample diagnostic methods. Experimental results demonstrate the effectiveness and superiority of the proposed SMSRFFN in mining fault information and improving diagnosis accuracy under extremely small sample conditions.

Dynamic simulation-assisted Gaussian mixture alignment approach for fault diagnosis of rotation machinery under small samples

“…In engineering scenarios, fault diagnosis often suffers from imbalances or small samples issues [11]. The acquisition of operational fault data is constrained by equipment operating conditions and the complexity of failure analysis, whereas label data require expert knowledge to analyze monitoring signals through intricate signal processing techniques [12]. When confronted with the challenge of fault diagnosis in scenarios with limited sample sizes, direct application of deep learning and transfer learning models is not feasible.…”

Small-sample Engine Fault Diagnosis Method Based on IACGAN and DNNs

“…Aero engines, in particular, have even higher reliability requirements. Early detection of ICE faults enables timely repair and minimizes property damage [1]. Today, data-driven deep learning methods are the most popular fault detection techniques [2].…”