Showing papers in "Reliability Engineering & System Safety in 2022"

TL;DR: This paper aims at pointing out main challenges and directions of advancements, for full deployment of condition-based and predictive maintenance in practice, for Prognostics and Health Management and its benefits in practice.

TL;DR: In this paper , a bidirectional gated recurrent unit with temporal self-attention mechanism (BiGRU-TSAM) was proposed to predict the remaining useful life (RUL) of an aircraft turbofan engine.

TL;DR: This review work digs into the problem essence of the DE3 of PHM by reviewing the research work, extracting the research conclusions from 235 related publications, and exposing the current methodologies and solution frameworks for addressing theDE3 issues.

TL;DR: In this article , a novel convexity-oriented time-dependent reliability-based topology optimization (CTRBTO) framework is investigated with overall consideration of universal uncertainties and time-varying natures in configuration design.

TL;DR: A case study on FEMTO-ST datasets shows that the fine-tuned model is competent for incipient fault detection, outperforming other state-of-the-art methods.

TL;DR: Wang et al. as discussed by the authors explored the fault diagnosis in a probabilistic Bayesian deep learning framework by exploiting an uncertainty-aware model to understand the unknown fault information and identify the inputs from unseen domains.

TL;DR: In this paper , a predictive analytics method utilizing the Lempel-Ziv algorithm and the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) for traffic safety management is proposed.

TL;DR: In this article, the authors proposed a statistical model for system reliability evaluation by jointly considering the correlated component lifetimes and the lifetime ordering constraints, and the point estimates of the model parameters as well as the lifetime quantiles are obtained by the maximum likelihood method and the confidence intervals are constructed using the generalized pivots.

TL;DR: In this article , the authors proposed a statistical model for system reliability evaluation by jointly considering the correlated component lifetimes and the lifetime ordering constraints, and the point estimates of the model parameters as well as the lifetime quantiles are obtained by the maximum likelihood method and the confidence intervals are constructed using the generalized pivots.

TL;DR: In this article , a trustworthy analysis with uncertainty-aware deep ensembles is conducted to detect the out-of-distribution (OOD) samples and issue the warnings for the potential untrustworthy diagnosis.

TL;DR: In this article , a failure rate correction model is proposed to map the relations of failure features between onshore and floating offshore wind turbines, and a Bayesian network is constructed to analyze the failure rate and reliability of the entire floating off-shore wind turbine.

TL;DR: In this article , a dual-task network structure based on bidirectional gated recurrent unit (BiGRU) and multi-gate mixture-of-experts (MMoE) was proposed to simultaneously evaluate the health status (HS) assessment and remaining useful life (RUL) prediction of industrial equipment.

TL;DR: In this article , a normalized convolutional neural network (NCNN) framework with batch normalization strategy is developed for feature extraction and fault identification of hydraulic piston pump, which can accurately and steadily complete the fault classification of hydraulic pump.

TL;DR: In this paper, a hybrid framework for fusing the information from physics-based performance models with deep learning algorithms for prognostics of complex safety-critical systems is proposed, which is based on a calibration problem to infer unobservable model parameters related to a system's components health.

TL;DR: Wang et al. as discussed by the authors proposed a blockchain-based decentralized federated transfer learning method for collaborative machinery fault diagnosis, where a tailored committee consensus scheme is designed for optimization of the model aggregation process.

TL;DR: An anomaly detection and diagnosis method for wind turbines using long shortterm memory-based stacked denoising autoencoders (LSTM-SDAE) and extreme gradient boosting (XGBoost) is proposed in this paper .

TL;DR: In this article, the authors proposed a novel deep learning method, i.e. variational mode decomposition long short-term memory (VMD-LSTM), for bus travel speed prediction in urban traffic networks using a forecast of bus arrival information on variable time horizons.

TL;DR: In this paper , a self-supervised pre-training via contrast learning (SSPCL) is introduced to learn discriminative representations from unlabeled bearing datasets, and a specific architecture for SSPCL deployment on bearing vibration signals by presenting several data augmentations for 1D sequences.

TL;DR: In this article , a double attention-based data-driven framework for aircraft engine RUL prognostics was proposed, where the channel attention was utilized to apply greater weights to more significant features and a Transformer was used to focus attention on these features at critical time steps.

TL;DR: Wang et al. as mentioned in this paper proposed a hybrid knowledge-based and data-driven approach for quantitative analysis of resilience in urban rail networks, where the aim is to model the causal relationships to quantify the importance of different perturbations to the overall resilience.

TL;DR: Wang et al. as discussed by the authors proposed a novel deep learning method, i.e. variational mode decomposition long short-term memory (VMD-LSTM), for bus travel speed prediction in urban traffic networks using a forecast of bus arrival information on variable time horizons.

TL;DR: A detailed review and analysis of techniques for human and organizational factors analysis in maritime transportation during 2000-2020 is presented in this paper , where various attempts have been made to reduce human errors by identifying the existing challenges.

TL;DR: Li et al. as discussed by the authors proposed a residual residual unit (RRSU)-based residual unit decomposition (RSU decomposition) to prevent effective information about the capacity regeneration part from being eliminated, which can reduce the number of input network components and lighten operating costs.

TL;DR: In this paper , a machine learning method was used to evaluate ship grounding risk in real environmental conditions using big data streams from Automatic Identification System (AIS), nowcast data, and seafloor depth data from the General Bathymetric Chart of the Oceans (GEBCO).

TL;DR: A review of the use of ML models in structural reliability analysis can be found in this article, which includes the most common types of ML methods used in SRA, including artificial neural networks (ANN), support vector machines (SVM), Bayesian methods and Kriging estimation with active learning perspective.

TL;DR: Wang et al. as mentioned in this paper proposed a novel open set domain adaptation network based on dual adversarial learning, where an auxiliary domain discriminator assigns similarity weights for individual target samples to distinguish between known and unknown fault modes.

TL;DR: A review of the machine learning-based structural reliability analysis methods is presented in this article , where the authors focus on the different models' structures and diverse applications of each ML method in different aspects of SRA.

TL;DR: In this article, a new learning function with a parallel processing strategy is proposed for selecting new training samples for complex systems, which combines dependent Kriging predictions and parallel learning strategy to further improve the computational efficiency.

TL;DR: In this article , the authors proposed joint importance measures for the optimal component sequence of a consecutive- k-out-of-n system, and analyzed the relationship between component reliability and joint importance measure under consideration of consecutive-k-out of n system structure changes.