Intelligent fault diagnosis methods have gained much attention in industry. An important premise of these methods is that the training and test data maintain the same set of fault classes, known as the closed-set hypothesis, which, however, cannot be guaranteed in fault diagnosis tasks. This can result in potentially unknown faults being incorrectly randomly classified as a known fault class. To overcome this problem, we introduce open-set recognition and proposed an Open Fault Semantic subspace-based open-set Fault Diagnosis and Inference framework (OFS-FDI), which identifies unknown faults while completing the diagnosis of a known class of faults, and furthermore, inferring the possible fault type of unknown samples. First, a fault semantic subspace construction method is proposed to transform the original signal into a set of low-dimensional representation subsets conforming to a conditional Gaussian distribution, which is related to the fault semantic. Then, an outlier score is proposed to determine whether a sample is from an unknown class. Finally, a class directional index (CDI) metric is proposed to perform inferential analysis of possible fault classes. In the experiments based on two typical rotating machines, the outlier detection accuracy of OFS-FDI is improved by up to 0.04% compared to the comparative methods. The accuracy for unknown fault inference is up to 99.65%.

The precise remaining useful life (RUL) prediction of turbofan engines benefits maintenance decisions. The training data quantity and quality are crucial for effective prediction modeling and accuracy improvement. However, the performance degradation process of the same type of turbofan engine usually exhibits different trajectories because of engines’ differences in degradation degrees, degradation rates, and initial health states. In addition, the initial part of the trajectory is a stationary health stage, which contains very little information on degradation and is not helpful for modeling. Considering the differential degradation characteristics and the requirement for accurate prediction modeling of the same type of turbofan engines with individual differences, we specifically propose a personalized transfer learning framework for RUL prediction by answering three key questions: when, what, and how to transfer in prediction modeling. The framework tries to maximumly utilize multi-source-domain data (samples of the same type of engines that run to failure) to improve the training data quantity and quality. Firstly, a transfer time identification method based on a dual-baseline performance assessment and the Wasserstein distance is designed to eliminate the worthless part of a trajectory for transfer and prediction modeling. Then, the transferability of each sample in the multi-source domain is measured by an approach, named the time-lag ensemble distance measurement, and then the source domain is ranked and adaptively deconstructed into two parts according to transferability. Ultimately, a new training loss function considering the transferability of the weighted multi-source-domain data and a two-stage transfer learning scheme is introduced into an informer-based RUL prediction model, which has a great advantage for long-time-series prediction. The simulation data of 100 of the same type of turbofan engine with individual differences and five comparison experiments validate the effectiveness and accuracy of the proposed method.