Search

This paper proposes an FMEA-BN model to determine the inspection and opportunistic maintenance strategies of floating offshore wind turbines. A mapping algorithm is proposed to establish a mirrored Bayesian Network (BN) model from a given failure mode and effect analysis (FMEA) structure to realize the FMEA-BN modelling, which is efficient to consider common cause failures. The failure probabilities of items of floating offshore wind turbines are first updated by the BN sub-model, in which, various operation scenarios are considered. The updated failure probabilities are then imported to the FMEA sub-model to determine the items of the floating offshore wind turbines that are to be inspected and to which the opportunistic maintenance action would be applied. With the FMEA-BN model, inspection and opportunistic maintenance strategies for a floating offshore wind turbine are suggested under several commonly occurring operation scenarios. The validation of the results is illustrated by the failure rate of the floating offshore wind turbine predicted by the BN sub-model, the uncertainty of which is lower than 3%. Overall, the presented FMEA-BN model supports real-time inspection and opportunistic maintenance strategies determination of complicated systems like floating offshore wind turbines. • FMEA-BN is proposed to determine the inspection and opportunistic maintenance strategies of floating offshore wind turbines. • A mapping algorithm is proposed to establish a Bayesian Network model from a given failure mode and effect analysis (FMEA). • The failure probabilities of items of floating offshore wind turbines are first updated by the BN sub-model. • The updated failure probabilities are then imported to the FMEA sub-model to determine the items that are to be inspected. • The presented FMEA-BN model supports real-time inspection and opportunistic maintenance strategies. [ABSTRACT FROM AUTHOR]

Data-driven fault diagnosis methods have significantly contributed to the rapid development of prognostics and health management of gearboxes. However, these methods require sufficient labeled data for model training. In real industrial scenarios, labeled data is usually scarce. Thus, a residual attention temporal recurrent network is proposed for fault diagnosis of gearboxes under limited labeled data. More specifically, a fault diagnosis framework with self-supervised sample generation learning is explored in this paper. First, a small amount of labeled data is utilized to self-supervise the generation of new samples with similar semantics in adversarial generation modeling. Second, a temporal recurrent network with residual attention is constructed to extract fault features of vibration signals using two-stage temporal and recursive operations. In addition, the construction of the residual attention mechanism can facilitate the network to have a deeper semantic understanding of the vibration signal. Finally, the model can guarantee a more robust classifier in the proposed fault diagnosis framework using a small number of labeled samples. The extensive validation of the proposed method is performed on the gearbox dataset. The experimental results show that the proposed method can achieve competitive fault diagnosis performance under limited labeled data. • The main contributions of this paper are as follows. • A residual attention temporal recurrent network is proposed for the fault diagnosis. • A two-stage feature extractor embedded with a residual attention mechanism is constructed. • An adversarial generation module is developed to obtain new samples with similar semantics. [ABSTRACT FROM AUTHOR]

• A novel hybrid prognostic method for remaining useful life prediction is presented. • A new nonlinear health indicator is generated for the training bearings. • The condition monitoring interval of health state is determined by the 3σ criterion. • The degradation and RUL forecasting is achieved based on the nonlinear Wiener process with random effects method. This paper proposes a novel hybrid method aiming at the fault prognosis of bearings. A nonlinear health indicator (HI) is first constructed using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise and Kernel Principal Component Analysis to reflect the health state of a bearing accurately and convincingly. Subsequently, multi-domain features are extracted from vibration signals and the Dual-Channel Transformer Network with the Convolutional Block Attention Module is applied for constructing HIs of the rest bearings. Moreover, the 3σ criterion is employed to establish the condition monitoring interval of health state and detect the First Prediction Time, with which degradation modeling and probabilistic Remaining Useful Life (RUL) prediction are conducted with the assistance of nonlinear Wiener process with random effects. The superior performance of the proposed hybrid prognostic method confirms that the method contributes to the accurate RUL prediction and uncertainty quantification. [ABSTRACT FROM AUTHOR]