Deep learning-based approach has emerged as a promising solution to handle big machinery data from multi-sensor suites in complex physical assets and predict their remaining useful life (RUL). However, most recent deep learningbased approaches deliver a single-point estimate of RUL as these models represent the weights of a neural network as a deterministic value and hence cannot convey uncertainty in the RUL prediction. This practice usually provides overly confident predictions that might cause severe consequences in safetycritical industries. To address this issue, this paper proposes a probabilistic Bayesian recurrent neural network (RNN) for RUL prognostics considering epistemic and aleatory uncertainties. The epistemic uncertainty is handled by Bayesian RNN layers as extensions from the Frequentist RNN layers using the Flipout method. The aleatory uncertainty is covered by a probabilistic output that follows a Gaussian distribution parameterized by the two neurons in the output layer. The network is trained using Bayes by backprop with the Flipout method. The proposed model is demonstrated by the open-access Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset of turbofan engines and a comparative study of the Frequentist RNN counterparts, the Monte Carlo Dropout-based RNN, and the state-of-the-art models for C-MAPSS datasets. The results demonstrate the promising performance and robustness of the proposed model in RUL prognostics.
In the application of the lattice Boltzmann method (LBM) for the simulation of the interface-resolved particulate flows, the bounce-back (BB) type rules have been widely adopted to handle the complex boundaries of moving particle. However, the original method cannot preserve the integrity of the particle shape, resulting in a low-resolution for the flow description near the solid boundary. Even though the subsequent modified BB scheme, i.e. the curved boundary condition (CBC), improves the overall accuracy, it generally loses the local-computation property of the simple BB. Therefore, a CBC is proposed in this paper, which maintains the two advantages of the second-order accuracy and local computation in the boundary treatment simultaneously. In the present scheme, information of only a single fluid point is needed. Furthermore, the relative distance between the fluid point and the boundary surface is involved, contributing to the second-order accuracy that is validated in the Poiseuille and cylindrical Couette flows. Particularly, it is found that the precision of the present scheme can be greatly improved with the nonequilibrium distribution functions of two directions included. Three more test cases of particle-laden flow, including particle migration in a channel, the sedimentation of a particle under gravity and the drafting-kissing-tumbling (DKT) dynamics of two settling particles, further demonstrate the feasibility and accuracy of the present scheme.
Data-driven machine learning (DDML) methods for the fault diagnosis and detection (FDD) in the nuclear power plant (NPP) are of emerging interest in the recent years. However, there still lacks research on comprehensive reviewing the state-of-the-art progress on the DDML for the FDD in the NPP. In this review, the classifications, principles, and characteristics of the DDML are firstly introduced, which include the supervised learning type, unsupervised learning type, and so on. Then, the latest applications of the DDML for the FDD, which consist of the reactor system, reactor component, and reactor condition monitoring are illustrated, which can better predict the NPP behaviors. Lastly, the future development of the DDML for the FDD in the NPP is concluded.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.