scispace - formally typeset
Search or ask a question

Showing papers in "Reliability Engineering & System Safety in 2020"


Journal ArticleDOI
TL;DR: A novel deep transfer learning model called multi-scale deep intra-class adaptation network is constructed, which first uses the modified ResNet-50 to extract low-level features and then constructs a multiple scale feature learner to analyze these low- level features at multiple scales and obtain high-level Features as input for the classifier.

163 citations


Journal ArticleDOI
TL;DR: A new data-driven approach for domain adaptation in prognostics using Long Short-Term Neural Networks (LSTM) is proposed that uses a time window approach to extract temporal information from time-series data in a source domain with observed RUL values and a target domain containing only sensor information.

157 citations


Journal ArticleDOI
TL;DR: An ensemble approach that integrates the Rul estimations obtained from the similarity-based curve matching techniques, with and without the zero-centering rules, is introduced to increase the robustness and accuracy of proposed method for RUL estimations.

125 citations


Journal ArticleDOI
TL;DR: This work reviews literature on six CINs, namely, water, drainage, gas, transportation, electric, and communication networks, and the resilience definitions, hazard categories, methodologies, and enhanced measures for each CIN are analyzed in detail.

121 citations


Journal ArticleDOI
TL;DR: The work pioneers the analysis of various impacts of human factors on different maritime accident types and helps provide specific recommendations for the prevention of a particular type of accidents involving human errors.

113 citations


Journal ArticleDOI
TL;DR: A novel approach to assess the time-dependent resilience of engineering systems using resilience indicators using the Dynamic Bayesian Network (DBN), a mathematical probabilistic framework based on the DBN is developed to model the resilience of dynamic engineering systems.

112 citations


Journal ArticleDOI
TL;DR: A systematic review of the journal articles on FMEA improvement during the years between 1998 and 2018 is conducted to present an overview of publication distribution across time and journals and identify the most influential authors, institutions and areas.

109 citations


Journal ArticleDOI
TL;DR: This paper defines the two modes of safety management and explains the challenges in changing the role of a safety professional to support Safety-II, and outlines specific activities for safety professionals to adopt in their role to move towards a guided adaptability mode ofSafety-II.

106 citations


Journal ArticleDOI
TL;DR: This paper performs model forecasting accuracy comparison analysis for a proposed random forest method, which dramatically improves the prediction accuracy without providing additional false negative predictions or false positive predictions which are known as false alarms.

104 citations


Journal ArticleDOI
TL;DR: The results indicate that SALK can locally approximate the limit-state surfaces around the finalSRBDO solution and efficiently reduce the computational cost on the refinement of the region far from the final SR BDO solution.

102 citations


Journal ArticleDOI
TL;DR: A Weibull proportional hazards model is proposed to jointly model the degradation data and the failure time data so that the degradation does not directly lead to system failures, but increases the hazard rate of hard failures.

Journal ArticleDOI
TL;DR: A methodology to predict pipe failures in water supply networks and the results obtained state that the number of unexpected failures might be significantly reduced, which is a realistic and feasible option.

Journal ArticleDOI
TL;DR: A realistic cascading model for multi-sink WSNs is proposed, and there are critical thresholds for both node capacity and link capacity, which can determine whether capacity expansion is helpful and whether cascading failures occur.

Journal ArticleDOI
TL;DR: The framework presented in the paper is the first step towards supervisory risk control, i.e., developing control systems for autonomous systems with risk management capabilities to improve the decision-making and intelligence of such systems.

Journal ArticleDOI
TL;DR: A flexible class of bivariate stochastic processes are proposed to incorporate the effects of environmental stress variables and the dependency between two degradation processes is modeled by a copula function in a bivariate degradation model of a coherent system.

Journal ArticleDOI
TL;DR: The aim of this paper is to model and assess the interdependency between inland port infrastructure and its surrounding supply chain and to show how the disturbance in one will have a ripple effect and trigger cascading failures in the entire network.

Journal ArticleDOI
TL;DR: Focus is needed to build evidence of the validity of the models’ results, if these are to be effectively used for waterway risk analysis, and more focus is needed on how exactly non-accident critical events are defined, and what factors are involved in the relation between their occurrence and accident involvement.

Journal ArticleDOI
TL;DR: A stratified importance sampling method with an adaptive Kriging strategy to estimate failure probabilities and the efficiency of the proposed method is demonstrated using several analytic examples and then transferred to a carbon dioxide storage benchmark problem.

Journal ArticleDOI
TL;DR: In this paper, component state transitions are assumed to be caused by external shocks and multi-state balanced systems based on state distance and symmetric state distance are constructed in detail based on two specific balance functions.

Journal ArticleDOI
TL;DR: The H-SIA method analyses the system as whole, rather than focus on each component separately, allowing identification of dependent tasks between agents and visualization of propagation of failure between the agents’ tasks.

Journal ArticleDOI
TL;DR: The selective maintenance bi-objective optimization problem is modelled considering both the expected value and variance of the system reliability as objective functions and time and budget are considered as constraints for finding the optimal maintenance strategy.

Journal ArticleDOI
TL;DR: The review findings reveal that the applications of BNs in the wind energy industry are quite diverse, ranging from wind power and weather forecasting to risk management, fault diagnosis and prognosis, structural analysis, reliability assessment, and maintenance planning and updating.

Journal ArticleDOI
TL;DR: A systematic methodology towards a consistent definition of PHM architectures to ensure a more complete and consistent design during the development phase of the product lifecycle is presented and a generic PHM architecture in accordance with this systematic methodology is proposed.

Journal ArticleDOI
TL;DR: Numerical results show that significant cost savings and improved system reliabilities can be obtained by using more accurate predictive information in maintenance decision-making and the potential benefits of incorporating dynamic contexts.

Journal ArticleDOI
TL;DR: A hybrid formalism is proposed that strengthens SPN with BN capabilities and provides a dynamic assessment of safety by capturing additional sets of data rends and uses advance feature such as predicates to perform the data updating functions.

Journal ArticleDOI
TL;DR: This paper proposes a novel and flexible CBM model based on a customized deep reinforcement learning for multi-component systems with dependent competing risks, which makes the proposed model suitable for both low and high dimensional CBM.

Journal ArticleDOI
TL;DR: This work investigates the optimal mission abort policies for systems subject to a controllable shock process with self-healing mechanism and finds that the optimal policy is to minimize the expected total cost of mission failure, system failure and imperfect repair.

Journal ArticleDOI
TL;DR: The proposed method starts from the payoff of the more general evolutionary game phenomena in reality, and eliminates the nodes with negative payoff and the edges connected with the failed nodes, and shows that the aggregation and invulnerability coefficients of the scale-free network are on the rise.

Journal ArticleDOI
TL;DR: An improved UAV swarm model is proposed by incorporating the effect of limited communication range into the existing model and an improved resilience metric is proposed based on the difference between the swarm's performance and its standard system performance.

Journal ArticleDOI
TL;DR: It is investigated whether a CNN-based model can quickly and accurately interpret images constructed based on data from the Automatic Identification System in terms of collision risk and whether adding additional navigational information based on AIS data improves the model's predictive accuracy.