Reliability Engineering & System Safety最新文献

Surrogate modeling for probability distribution estimation: Uniform or adaptive design?

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-04-03 DOI: 10.1016/j.ress.2025.111059

Maijia Su , Ziqi Wang , Oreste Salvatore Bursi , Marco Broccardo

{"title":"Surrogate modeling for probability distribution estimation: Uniform or adaptive design?","authors":"Maijia Su , Ziqi Wang , Oreste Salvatore Bursi , Marco Broccardo","doi":"10.1016/j.ress.2025.111059","DOIUrl":"10.1016/j.ress.2025.111059","url":null,"abstract":"<div><div>The active learning (AL) technique, one of the state-of-the-art methods for constructing surrogate models, has shown high accuracy and efficiency in forward uncertainty quantification (UQ) analysis. This paper provides a comprehensive study on AL-based global surrogates for computing the full distribution function, i.e., the cumulative distribution function (CDF) and the complementary CDF (CCDF). To this end, we investigate the three essential components for building surrogates, i.e., types of surrogate models, enrichment methods for experimental designs, and stopping criteria. For each component, we choose several representative methods and study their desirable configurations. In addition, we use a uniform design based on maximin-distance criteria as a baseline for measuring the improvement of using AL. Combining all the representative methods, a total of 1920 UQ analyses are carried out to solve 16 benchmark examples. The performance of the selected strategies is evaluated based on accuracy and efficiency. In the context of full distribution estimation, this study concludes that (<em>i</em>) The benefit of using AL is lower than expected and varies across different surrogate models, with three reasons for this performance variability analyzed in detail. (<em>ii</em>) Detailed recommendations are provided for the three surrogate components, depending on the features of the problems (especially the local nonlinearity), target accuracy, and computational budget.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"261 ","pages":"Article 111059"},"PeriodicalIF":9.4,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143777322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Novel formulations and metaheuristic algorithms for predictive maintenance of aircraft engines with remaining useful life prediction

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-04-02 DOI: 10.1016/j.ress.2025.111064

Lubing Wang , Xufeng Zhao , Hoang Pham

{"title":"Novel formulations and metaheuristic algorithms for predictive maintenance of aircraft engines with remaining useful life prediction","authors":"Lubing Wang , Xufeng Zhao , Hoang Pham","doi":"10.1016/j.ress.2025.111064","DOIUrl":"10.1016/j.ress.2025.111064","url":null,"abstract":"<div><div>Advanced sensor technology has driven the remaining useful life (RUL) prediction of aircraft engines. However, only a few studies have considered incorporating RUL prediction results into maintenance plans. To address this problem, this paper investigates a novel predictive maintenance framework for aircraft engines. First, a hybrid deep learning model is developed to predict the aircraft engine RUL. Based on the predicted RUL, two new mixed integer linear programming models are developed to deal with the predictive maintenance problem of aircraft engines, which targets to minimize the maximum maintenance completion time for all aircraft engines. Since commercial solvers (e.g. CPLEX) solving it is time-consuming as the problem scale increases, we develop a new fast and effective hybrid metaheuristic algorithm based on the problem features, which combines a genetic algorithm and a variable neighborhood search algorithm. Finally, numerical experiments from the NASA aircraft engine dataset validate the proposed predictive maintenance framework can provide the optimal predictive maintenance plan in less than 10 s for large-scale maintenance problems, thereby reducing aircraft maintenance completion time.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"261 ","pages":"Article 111064"},"PeriodicalIF":9.4,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143777324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Two-stage propagation analysis of safety risks in complex underground engineering: An integrated modeling framework

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-04-01 DOI: 10.1016/j.ress.2025.111081

Yuanwen Han , Jiang Shen , Xuwei Zhu , Xueying Bao

{"title":"Two-stage propagation analysis of safety risks in complex underground engineering: An integrated modeling framework","authors":"Yuanwen Han , Jiang Shen , Xuwei Zhu , Xueying Bao","doi":"10.1016/j.ress.2025.111081","DOIUrl":"10.1016/j.ress.2025.111081","url":null,"abstract":"<div><div>The complex nonlinear mapping relationships among safety risks in underground engineering projects provide various potential pathways for risk propagation. A lack of understanding of the propagation behavior of risks can lead to improper risk prevention and control, which may trigger chain reactions of safety accidents. To address this issue, this study quantified and visualized the interactions among safety risks in complex underground engineering by coupling association rule mining and complex networks. It also examined the propagation process of risk factors under different intervention measures, considering managers' preferences (intervention intensity and timing), using an improved epidemiological model. The results show that for the same risk, the risk-control effectiveness of different stakeholders as controlled factors varies significantly. Government and regulatory departments, as well as project owners, should play a leading role in safety risk management, whereas contractors' unsafe behaviors, material and equipment factors, and environmental factors, when used as intervention factors, show poorer risk control effectiveness. Managers' preferences affect the peak and convergence times of risk propagation, and a more conservative approach is more favorable for risk control. This study recommends that managers increase the frequency of detecting abnormal conditions to promptly identify latent risks and implement early intervention measures to prevent their spread. This study constructed a dynamic risk propagation analysis framework for complex underground engineering projects. It contributes to the understanding of the formation mechanisms of underground engineering safety risks and provides decision support to implement precise risk interventions, thereby promoting the achievement of engineering safety goals.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"261 ","pages":"Article 111081"},"PeriodicalIF":9.4,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143777323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Microgrid-level reliability assessment of mid-term electricity provision under intermittency of renewable distributed generation: A probabilistic conditional value at risk modeling

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-04-01 DOI: 10.1016/j.ress.2025.111087

Seyed-Sadra Jodeiri-Seyedian , Mohammad Veysi

{"title":"Microgrid-level reliability assessment of mid-term electricity provision under intermittency of renewable distributed generation: A probabilistic conditional value at risk modeling","authors":"Seyed-Sadra Jodeiri-Seyedian , Mohammad Veysi","doi":"10.1016/j.ress.2025.111087","DOIUrl":"10.1016/j.ress.2025.111087","url":null,"abstract":"<div><div>In critical and sensitive load sites like medical and educational microgrids (MGs), the reliability index holds paramount importance, yet it has not received necessary attention. This paper introduces a scheduling strategy focused on maximizing the MG's annual reliability index. Here, a power-based failure rate (PFR) concept to enhance the reliability assessment of MGs, establishing a relationship between component failure rates and production, is proposed. Moreover, MGs face various uncertainties, including renewable energy resources’ generation and consumption patterns. These uncertainties are modeled using a scenario-based stochastic approach with well-known probability density functions. Furthermore, the potential risks of the worst-case scenario present a significant obstacle to the reliability-focused improvement process; to safeguard the suggested framework from undesirable conditions, a conditional value at risk (CVaR)-based framework is developed. This framework assists the MG operator (MGO) in managing the analyzed system during worst-case scenarios. Ultimately, the proposed model encountered a non-convex challenge due to the exponential nature of reliability and PFR curves, which transformed into a mixed integer linear programming model utilizing piecewise linearization and the MacCormack relaxation techniques. Simulation findings indicate that under full-risk conditions, the annual reliability index of MGs slightly decreases due to the MGO's conservative policies.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"261 ","pages":"Article 111087"},"PeriodicalIF":9.4,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143768373","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Trustworthy interval prediction method with uncertainty estimation based on evidence neural networks

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-03-31 DOI: 10.1016/j.ress.2025.111086

Peng Han , Zhiqiu Huang , Weiwei Li , Wei He , You Cao

{"title":"Trustworthy interval prediction method with uncertainty estimation based on evidence neural networks","authors":"Peng Han , Zhiqiu Huang , Weiwei Li , Wei He , You Cao","doi":"10.1016/j.ress.2025.111086","DOIUrl":"10.1016/j.ress.2025.111086","url":null,"abstract":"<div><div>Developing accurate and reliable prediction models is critical to ensuring the safety of the system. However, traditional deep learning only provides point predictions is not enough. For some high-risk systems, such as aerospace and autonomous driving, the reliability of model predictions needs to be assessed. This requires quantifying the uncertainty of model predictions and constructing trustworthy prediction intervals. Thus, a new trustworthy interval prediction method based on evidence neural network (TIENN) is proposed. Firstly, evidence theory and the Dirichlet distribution are integrated into deep neural networks to quantify prediction uncertainty. Secondly, modified expected utility theory is used to construct trustworthy prediction intervals. Moreover, a new loss function is designed to achieve both accurate point predictions and high-quality prediction intervals. Finally, taking the lithium-ion battery interval capacity prediction as an example to verify the effectiveness of the TIENN. The output results of the TIENN can not only be explained in clear language semantics, but also are consistent with the degradation process of lithium-ion batteries in actual engineering, thereby improving decision makers' trust in the model.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"261 ","pages":"Article 111086"},"PeriodicalIF":9.4,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143768439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improving reliability of safety countermeasure evaluation at highway-rail grade crossings through aleatoric uncertainty modeling with machine learning techniques

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-03-31 DOI: 10.1016/j.ress.2025.111082

Mohammadali Zayandehroodi , Barat Mojaradi , Morteza Bagheri

{"title":"Improving reliability of safety countermeasure evaluation at highway-rail grade crossings through aleatoric uncertainty modeling with machine learning techniques","authors":"Mohammadali Zayandehroodi , Barat Mojaradi , Morteza Bagheri","doi":"10.1016/j.ress.2025.111082","DOIUrl":"10.1016/j.ress.2025.111082","url":null,"abstract":"<div><div>Traditional Collision Modification Factor (CMF) calculation methods rely on simplistic statistical models that often fail to account for the complex, non-linear relationships influencing collision rates, leading to uncertain estimates. To address this gap, this study aims to improve the reliability of CMF estimation for safety countermeasures by introducing a novel hybrid model that combines Negative Binomial (NB) regression with a Long Short-Term Memory (LSTM) neural network to estimate aleatoric uncertainty. In other words, the proposed method integrates statistical modelling with machine learning techniques within the Empirical Bayes (EB) framework to compute uncertainty for enhancing CMF accuracy and stability. By increasing the reliability of collision frequency predictions and calculating more precise CMFs, the proposed method enables the selection of appropriate countermeasures, ultimately reducing fatalities and costs. The model is trained using data from Highway-Rail Grade Crossings (HRGC) inventory and collision records from the Federal Railroad Administration (FRA) for 2016–2022. The NB regression model provides a statistical foundation for collision prediction, while the LSTM component models uncertainties, significantly improve CMF calculation. Compared to the traditional NB model, the hybrid NB-LSTM approach reduces root mean squared error (RMSE) by 62.5 % and mean absolute error (MAE) by 61 % in predicting collision frequencies, leading to more reliable CMFs. The model identifies that gates reduce collisions by 61 % in high-traffic HRGCs, bells decrease collisions by 67 % in high-speed areas, and flashing lights achieve a 72 % reduction in low-traffic, high-speed crossings. Additionally, the proposed method achieves lower standard errors (S.E.) across all countermeasures.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"261 ","pages":"Article 111082"},"PeriodicalIF":9.4,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143747722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A methodology of natural gas pipeline network system supply resilience optimization: Based on demand-side and data science-driven approach

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-03-30 DOI: 10.1016/j.ress.2025.111071

Zhiwei Zhao , Zhaoming Yang , Huai Su , Michael H. Faber , Jinjun Zhang

{"title":"A methodology of natural gas pipeline network system supply resilience optimization: Based on demand-side and data science-driven approach","authors":"Zhiwei Zhao , Zhaoming Yang , Huai Su , Michael H. Faber , Jinjun Zhang","doi":"10.1016/j.ress.2025.111071","DOIUrl":"10.1016/j.ress.2025.111071","url":null,"abstract":"<div><div>This paper proposes a method for optimizing the supply resilience of natural gas pipeline networks, driven by demand-side dynamics and data science. The method is divided into two main components: user demand characteristic modeling and system supply resilience optimization modeling. In the user demand characteristic modeling phase, preprocessed user demand data is used, combining the Tabular Variational Autoencoder (TVAE) with probability density distribution curve fitting to provide an in-depth characterization of user demand patterns. For the system supply resilience optimization modeling, constraints are established based on the functional characteristics of the system's components, and specific objective functions are designed for different operational scenarios. Additionally, the Latin Hypercube Sampling (LHS) method is employed to capture fluctuations in user demand. Finally, this paper introduces a set of evaluation indicators for gas supply resilience and validates the proposed methodology through five scenario-based case studies. The results confirm the effectiveness and feasibility of this approach in improving the resilience of natural gas pipeline systems.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"261 ","pages":"Article 111071"},"PeriodicalIF":9.4,"publicationDate":"2025-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143747723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Domain generalization network based on inter-domain multivariate linearization for intelligent fault diagnosis

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-03-29 DOI: 10.1016/j.ress.2025.111055

Wei Guan , Shuai Wang , Zeren Chen , Guoqiang Wang , Zhengbin Liu , Da Cui , Yiwei Mao

{"title":"Domain generalization network based on inter-domain multivariate linearization for intelligent fault diagnosis","authors":"Wei Guan , Shuai Wang , Zeren Chen , Guoqiang Wang , Zhengbin Liu , Da Cui , Yiwei Mao","doi":"10.1016/j.ress.2025.111055","DOIUrl":"10.1016/j.ress.2025.111055","url":null,"abstract":"<div><div>Intelligent fault diagnosis technology determines the safety and reliability of equipment operation, and domain-based adaptive fault diagnosis models have been explored for solving the problem of data distribution discrepancies caused by different operating conditions. However, the requirement of obtaining the unlabeled target domain data in advance limits its application in real-world equipment operating scenarios. To address this problem, this paper proposes an inter-domain multivariate linearization (IML)-guided domain generalization network (IMLNet) for intelligent fault diagnosis. A domain multivariate fusion generation module is designed to construct new domains by linearizing between different domains using inter-domain multivariate linearization, which helps the network to extract domain invariant features in depth. Meanwhile, by fusing the multi-attention mechanism and feature pyramid network on the basis of residual network, it promotes the network to capture multi-scale information and provide richer semantic information. The effectiveness of the method is verified through two different fault diagnosis cases.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"261 ","pages":"Article 111055"},"PeriodicalIF":9.4,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143739303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fault semantic knowledge transfer learning: Cross-domain compound fault diagnosis method under limited single fault samples

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-03-28 DOI: 10.1016/j.ress.2025.111050

Huaitao Xia , Tao Meng , Zonglin Zuo , Wenjie Ma

{"title":"Fault semantic knowledge transfer learning: Cross-domain compound fault diagnosis method under limited single fault samples","authors":"Huaitao Xia , Tao Meng , Zonglin Zuo , Wenjie Ma","doi":"10.1016/j.ress.2025.111050","DOIUrl":"10.1016/j.ress.2025.111050","url":null,"abstract":"<div><div>The coupling of faults leads to an exponential growth of compound fault types, making it impractical to collect complete labeled compound fault data in real-world scenarios. While cross-domain compound fault diagnosis (the target-domain does not have labeled compound fault data) is crucial for system reliability, existing methods often rely on abundant single-fault samples and rarely validate the reliability when single-fault data is limited. To overcome this limitation, we propose a novel fault semantic knowledge transfer learning framework. Specifically, FSKTL incorporates inter-class semantic distance loss in the source-domain, enabling fault classification through low-dimensional fault semantics and identifying the optimal fault semantic correlation function. Subsequently, FSKTL introduces inter-domain semantic alignment loss in the target-domain. This approach not only preserves the semantic space optimized by the source-domain for fault classification, but also achieves domain adaptation, enhancing the cross-domain generalization of the optimal fault semantic correlation function. Finally, extensive experiments are conducted on two publicly available datasets to validate the effectiveness of the proposed method. The results demonstrate that compared to other methods, this approach achieves the highest accuracy in cross-domain compound and single fault diagnosis.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"260 ","pages":"Article 111050"},"PeriodicalIF":9.4,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143747434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Applying incremental learning in binary-addition-tree algorithm in reliability analysis of dynamic binary-state networks

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-03-28 DOI: 10.1016/j.ress.2025.111072

Zhifeng Hao , Wei-Chang Yeh

引用次数: 0