Many factors affect the accuracy of the estimation of the remaining useful life (RUL) of the fan slewing bearings, thereby limiting the sustainable development of the wind power industry. More specifically, the traditional vibration data, which are easily disturbed by noises, cannot comprehensively characterize the health status; thus, the physical model is difficult to establish, and when the data-driven model analyzes the status, it results in unclear physical mechanisms. A new nonlinear Wiener degradation model was established based on the fusion of the physical models and the data-driven models, which was employed to characterize the degradation process of the slewing bearings in this work, and for the local temperature distribution, which has a strong anti-interference ability, the multi-sensor temperature data fusion was selected to analyze the RUL prediction. First, the multi-sensor temperature data were fused by performing a principal component analysis (PCA) to obtain the comprehensive health index (CHI), which represents the fan slewing bearings. Second, the Arrhenius Equation, which characterizes the degradation using temperature, was introduced into the nonlinear Wiener model, and a new degradation model was established. Moreover, considering the random change of the drift coefficients and the individual differences, the closed expression of the probability density function (PDF) of RUL was derived. Third, maximum likelihood estimation (MLE) was used to estimate the parameters. In addition, Bayesian analysis was used to update parameters to achieve real-time estimation. The results demonstrated that the proposed method can be used to significantly improve the fitting degree of the model and the accuracy of RUL estimation.

Incomplete diagnostic information, inadequate multisource sensor information, weak diagnosis models, and subjective experience result in difficulty in predicting rotating machinery faults. To overcome these limitations, we proposed a multiple domain and heterogeneous information entropy fusion model based on an optimisation of bearing fault diagnosis. The spatiotemporal approach uses a multiscene domain fusion strategy based on heterogeneous sensors (HSMSF) to extract feature fusion strategies and analyses the characteristics of the bearing fault features by multichannel processes with convolutional neural networks to vibration signals. After the mapping of multiple quality characteristics, the high-quality features are combined with each other, and the adaptive entropy weighted fusion method is used to analyse and make decisions on sensor information from different detection points. Nineteen key model parameters that were required for HSMSF construction were selected by adaptive optimisation using the chaos elitist modified sparrow search algorithm (CEI-SSA), and a self-learning diagnostic model that is suitable for multiple detection points was constructed. The validity and feasibility of the proposed fault diagnosis method were verified experimentally on two common reference-bearing datasets, CWRU and IMS, and compared with other fault diagnosis methods.

Traditional fault diagnosis methods for rolling bearings rely on nemerous labeled samples, which are difficult to obtain in engineering applications. Moreover, when unseen fault categories appear in the test set, these models fail to achieve accurate diagnoses, as the fault categories are not represented in the training data. To address these challenges, a zero-shot fault diagnosis model for rolling bearings is proposed, which realizes knowledge transfer from seen to unseen categories by constructing attribute information, thereby reducing the dependence on labeled samples. First, an attribute method Discrete Label Embedding Method (DLEM) based on word embedding and envelope analysis is designed to generate fault attributes. Fault features are extracted using the Swin Transformer model. Then, the attributes and features are input into the constructed model Distribution Consistency and Multi-modal Cross Alignment Variational Autoencoder (DCMCA-VAE), which is built on Convolutional Residual SE-Attention Variational Autoencoder (CRS-VAE). CRS-VAE replaces fully connected layers with convolutional layers and incorporates residual connections with the Squeeze-and-Excitation Joint Attention Mechanism (SE-JAM) for improved feature extraction. The DCMCA-VAE also incorporates a reconstruction alignment module with the proposed distribution consistency loss $L_{WT}$ and multi-modal cross alignment loss function $L_{MCA}$. The reconstruction alignment module is used to generate high-quality features with distinguishing information between different categories for classification. In the face of multiple noisy datasets, this model can effectively distinguish unseen categories and has stronger robustness than other models. The model can achieve 100% classification accuracy on the SQ dataset, and more than 85% on the CWRU dataset when unseen and seen categories appear simultaneously with noise interference.