scispace - formally typeset
Search or ask a question

Showing papers in "Reliability Engineering & System Safety in 2023"



Journal ArticleDOI
TL;DR: In this paper , the authors proposed a prognostic driven dynamic predictive maintenance (PdM) framework by integrating the two stages, i.e., prognostic and maintenance decision-making, for complex industrial systems.

20 citations


Journal ArticleDOI
TL;DR: In this article , an improved dual closed-loop observation modeling strategy, an improved anti-noise adaptive long short-term memory (ANA-LSTM) neural network with high-robustness feature extraction and optimal parameter characterization is proposed for accurate RUL prediction.

19 citations


Journal ArticleDOI
Jiusi Zhang, Xiang Li, Jilun Tian, Hao Luo, Shen Yin 
TL;DR: Li et al. as mentioned in this paper proposed a novel integrated multi-head dual sparse self-attention network (IMDSSN) based on a modified Transformer to predict the remaining useful life (RUL).

17 citations


Journal ArticleDOI
TL;DR: In this paper , the authors proposed a new framework for partial and open-partial domain adaptation based on generating distinct fault signatures with a Wasserstein GAN, which is suited for domain adaptation tasks with extreme label space discrepancies.

9 citations


Journal ArticleDOI
TL;DR: Support vector machine (SVM) is a powerful machine learning technique relying on the structural risk minimization principle as mentioned in this paper , which has been used extensively in structural reliability analysis (SRA) applications.

9 citations


Journal ArticleDOI
TL;DR: In this article , a tolerance optimization model is presented to minimize the failure probability of positioning accuracy with the constraint of manufacturing cost, and an improved genetic algorithm is then presented based on the diversity crossover and differential mutation strategies to optimally and efficiently solve the tolerance design model.

8 citations


Journal ArticleDOI
TL;DR: In this article , a digital twin-driven approach for implementing fault diagnosis of rolling bearings with insufficient training data is proposed, which establishes a virtual representation of a physical entity to mirror its operating conditions.

7 citations


Journal ArticleDOI
TL;DR: In this paper , the use of a long short-term memory (LSTM)-based multi-input neural network for degradation modeling and prediction of an Electro-Hydrostatic Actuator (EHA) system was proposed.

7 citations


Journal ArticleDOI
TL;DR: In this paper , a robust methodological approach, Failure Mode Effects and Criticality Analysis (FMECA), was used to provide a detailed insight into operational hazards, and Evidential Reasoning (ER) and Rule-based Bayesian Network (RBN) was used by evaluating the hazards' importance degrees.

7 citations


Journal ArticleDOI
TL;DR: In this article , a Dynamic Object-Oriented Bayesian Network (DOOBN) model has been developed for the purpose of analyzing the interactions of risk factors in internal corrosion.

Journal ArticleDOI
TL;DR: In this paper , the degradation tendency information from the physics-based stochastic degradation model was combined with machine learning approaches for degradation prediction with bias correction, and the results showed that the proposed hybrid method outperformed other machine learning-based methods.

Journal ArticleDOI
TL;DR: In this article , a failure behavior judgment method is proposed by using the convolutional autoencoder (CAE) and Pearson correlation coefficient to determine whether the bearing fails gradually or suddenly, and a multi-channel transfer network is proposed for extracting multi-scale features of bearing degradation.

Journal ArticleDOI
TL;DR: In this article , a data-driven Bayesian network approach with spatiotemporal fragility model is developed to investigate the dependencies between lightning strike and overhead contact lines (OCLs) of high-speed railway.

Journal ArticleDOI
TL;DR: In this paper , a self-adaptive dynamic clustering approach is developed to select useful multimodal data into different clusters, each of which has a consistent degradation tendency, and a cluster-ensemble transfer regression network is constructed by building multiple regressors for different clusters to predict the RUL values of aero-engine under cross-working conditions, where a multi-level feature learning strategy is provided to learn the domain invariant temporal degradation knowledge.

Journal ArticleDOI
TL;DR: In this article , a pipeline machine learning model is used to forecast tunnel-induced damage that can be addressed using the robust optimization (RO) algorithm with high accuracy, and the optimization process is integrated into a building information modeling (BIM) platform and analyzed using the Shapley Additive Explanations (SHAP) technique, allowing the designer to understand and interact with the algorithm.

Journal ArticleDOI
TL;DR: In this paper , a multi-phase Wiener process-based degradation model is constructed to characterize the degradation process subjected to imperfect maintenance activities, and the residual degradation coefficient caused by the imperfect maintenance activity is estimated through the maximum likelihood estimation and Newton iteration method.

Journal ArticleDOI
TL;DR: In this paper , the authors conduct a systematic review covering the methodological development of regional seismic risk assessment (RSRiA) across its key modules, including hazard analysis, exposure modeling, fragility assessment, and consequence evaluation, as well as the associated uncertainty quantification and propagation.

Journal ArticleDOI
TL;DR: In this article , the authors proposed a system-theoretic approach to safety analysis for human-system collaboration in maritime autonomous surface ships (MASS), where the authors defined operational contexts of MASS and integrated a human cognitive model into the system theoretic process analysis (STPA), called STPA-Cog.

Journal ArticleDOI
TL;DR: Zhang et al. as mentioned in this paper proposed a new state of health prediction method by using the gated recurrent unit neural networks and the hidden Markov model with considering uncertainty quantification.


Journal ArticleDOI
TL;DR: In this article , the basic GO methodology is extended to support the modeling and analysis of multi-state linear and circular consecutive-k-out-of-n: F system (MLC(k,n) &MCC(k-n)) models.

Journal ArticleDOI
TL;DR: In this paper , an interval dimension-wise analysis (IDWA) method is proposed to predict the uncertain state response of the uncertain attitude-vibration control system, which can help solve the overestimation problem of the conventional perturbation method.


Journal ArticleDOI
TL;DR: In this paper , a maintenance strategy is developed for multi-state systems operating exposed to changing environment states, and a Markov decision process is formulated to model the problem, and the maintenance strategy can then be optimized.

Journal ArticleDOI
TL;DR: In this article , a hybrid Bayesian-Copula-based method for assessing the wind-induced risk of tall buildings incorporating various uncertainties is presented, where the epistemic uncertainty in the unknown model parameters is incorporated into the risk estimates by the total probability theory.

Journal ArticleDOI
TL;DR: In this paper , an adaptive vectorial surrogate modeling framework (AVSMF) is developed based on the vectorial modeling concept and adaptive modeling strategy, where the adaptive model strategy is adopted to determine the form of mathematical model of each objective in line with the cost function, the surrogate modeling strategy is regarded as the basis function for reflecting the relationship of the output of single-objective between the relevant inputs, and matrix theory is used to ascertain the vectors and cell arrays of undetermined parameters and to establish the performance function of multiobjective structures.

Journal ArticleDOI
TL;DR: Wang et al. as mentioned in this paper proposed a cloud model-based approach to evaluate risk status of excavation, which consists of three phases: multi-sources information collection, construction of the benchmark cloud model (BCM), and risk level determination.

Journal ArticleDOI
TL;DR: In this article , an application method combining numerical simulation model and machine learning classification is proposed to show the advantages of digital twin, which can effectively predict the possibility of bearing failure synchronously and guide the adjustment and maintenance of actual bearing operating parameters.

Journal ArticleDOI
TL;DR: Wang et al. as mentioned in this paper proposed a tensor based domain adaptation method, which uses the time domain signals, the frequency domain signals and the Hilbert marginal spectrum and integrates them into a third-order tensor model.