A Novel Approach for Small-Sample Open-Set Fault Diagnosis in Rolling Bearings: Dense-ProtoNet-AE

Rolling bearings are key components of rotating machinery, and their health status directly affects the safety and stability of equipment operation. However, in actual industrial scenarios, due to factors such as high sensor deployment costs and low fault frequency, the number and types of fault samples are scarce, resulting in the coexistence of small sample problems and open set problems, forming the challenge of small sample open set fault diagnosis. Traditional deep learning methods are prone to overfitting when samples are insufficient, and the closed set assumption is difficult to deal with unknown faults, which limits the practicality of diagnosis. This paper takes rolling bearings as the research object and proposes an open set fault diagnosis method Dense-ProtoNet-AE under small sample conditions. Dense-ProtoNet introduces a prototype network based on CNN, realizes classification through embedded space representation and distance measurement, adopts a meta-learning framework for training, and introduces the DenseNet mechanism to enhance feature extraction capabilities, so as to realize closed set fault diagnosis of rolling bearings under small sample conditions. Autoencoder (AE) is used to design the open set recognition module, and AE is used to calculate the reconstruction error of known class samples. An adaptive multi-class 3σ method threshold selection strategy based on the validation set error is proposed to distinguish known classes from unknown classes. The known classes are then classified by Dense-ProtoNet closed set, thereby realizing small sample open set fault diagnosis.