Reliability Engineering & System Safety最新文献_第3页

Urban road network resilience assessment framework: Integrating spatiotemporal analysis with the resilience triangle and temporal performance indicators 城市路网弹性评价框架：时空分析与弹性三角和时间绩效指标相结合

IF 11 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-09-24 DOI: 10.1016/j.ress.2025.111742

Rouzbeh Azargoshasbi, Mohammad Ansari Esfeh, Lina Kattan

{"title":"Urban road network resilience assessment framework: Integrating spatiotemporal analysis with the resilience triangle and temporal performance indicators","authors":"Rouzbeh Azargoshasbi, Mohammad Ansari Esfeh, Lina Kattan","doi":"10.1016/j.ress.2025.111742","DOIUrl":"10.1016/j.ress.2025.111742","url":null,"abstract":"<div><div>Daily non-recurrent disruptions such as traffic collisions can significantly degrade the performance of urban road networks yet remain underexamined in resilience studies. This paper presents a data-driven framework that captures the spatiotemporal propagation and dissipation of these disruptions and evaluates link-level resilience through two sets of metrics. The proposed methodology uses multi-year travel time and incident data to build a relative network performance function, employing a time-dependent network efficiency metric adapted from complex network theory and adjusted for daily and weekly traffic variations. It consists of two main components: a spatiotemporal analysis using an adaptive statistical threshold to estimate occurrence and restoration times of disruptions, and a resilience assessment module that applies both resilience triangle and novel temporal performance metrics. The framework is applied to a real-world case study in downtown Calgary. It reveals that disruptions often begin before they are reported and persist well beyond clearance times, highlighting the limitations of incident records in capturing the true extent of network impact. Findings also indicate that low-resilience links are spatially clustered in high-demand, low-redundancy areas, with resilience loss in this case primarily driven by prolonged recovery. Incorporating temporal performance metrics further reveals degradation and recovery patterns, early drops, delayed recovery, and abrupt, symmetric transitions, that are not captured by traditional measures, offering deeper insight into timing and nature of performance changes. The proposed approach offers transportation agencies a multidimensional tool to better understand the resilience of urban road networks and guide targeted operational responses for daily disruptions.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111742"},"PeriodicalIF":11.0,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145267753","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

Identifying key regions in spatial networks through graph neural networks 利用图神经网络识别空间网络中的关键区域

IF 11 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-09-24 DOI: 10.1016/j.ress.2025.111743

Dingrong Tan , Mengxiang Zhang , Xiaoda Shen , Zhigang Wang , Ye Deng , Jun Wu

{"title":"Identifying key regions in spatial networks through graph neural networks","authors":"Dingrong Tan , Mengxiang Zhang , Xiaoda Shen , Zhigang Wang , Ye Deng , Jun Wu","doi":"10.1016/j.ress.2025.111743","DOIUrl":"10.1016/j.ress.2025.111743","url":null,"abstract":"<div><div>Complex systems are frequently modeled as spatially embedded networks, where nodes and edges are distributed within a physical space. A critical challenge in spatial network analysis is identifying key regions whose activation or removal of nodes and edges can significantly enhance or degrade network functionality with broad applications ranging from disease prevention and traffic congestion optimization. Although many advanced methods perform well in general topological networks, effective integration of topological and geographical features in the identification of critical regions remains unresolved. Here, we propose a novel spatial network disintegration model that employs square regions as the fundamental units of analysis, addressing the regional overlap issue inherent in circle-based disintegration models. We further introduce a deep learning framework, Key Region Identification with Graph Neural Networks (KRIG), trained on numerous small synthetic spatial networks to identify key regions in diverse real-world applications, including infrastructure and road networks. Extensive experiments validate that KRIG significantly outperforms existing approaches in detecting critical regions. The framework effectively balances topological and spatial characteristics through large-scale data-driven learning. The proposed deep learning framework opens up a new direction for analyzing spatial networks using deep learning techniques, which enables us to identify critical regions to resist attacks and failures and improve network reliability.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111743"},"PeriodicalIF":11.0,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220548","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

Bridging interactions and robustness of inter-community structures in disaster response systems: A hypergraph-based analysis 灾难响应系统中社区间结构的桥接交互和鲁棒性：基于超图的分析

IF 11 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-09-23 DOI: 10.1016/j.ress.2025.111732

Chong Gao , Hui Jiang , Xiaoling Guo

{"title":"Bridging interactions and robustness of inter-community structures in disaster response systems: A hypergraph-based analysis","authors":"Chong Gao , Hui Jiang , Xiaoling Guo","doi":"10.1016/j.ress.2025.111732","DOIUrl":"10.1016/j.ress.2025.111732","url":null,"abstract":"<div><div>Disaster response systems (DRS) are critical infrastructures that must remain functional under disruptive conditions. Due to the inherently modular nature of response operations, DRS often exhibit mesoscale inter-community structures that play a pivotal role in system-wide coordination and resilience. However, existing studies have largely overlooked the structural robustness of these inter-community patterns. To address this gap, we propose a hypergraph-based framework for modelling DRS, where hyperedges naturally capture high-order interactions among organizations. Within this framework, we focus on bridging interactions – hyperedges that connect different communities – and develop a metric to quantify their structural strength under perturbations. We then assess the robustness of inter-community structures through hypergraph dismantling experiments under random node failures and targeted attacks. Our results reveal that the fracturing of strong bridging interactions does not necessarily lead to system disintegration. Some weak bridging interactions act as important structural stabilisers. Moreover, we identify robustness-enhancing hubs, whose emergence is jointly determined by their hyperdegree and the strength of associated bridging interactions. By integrating hypergraph modelling with robustness analysis at the mesoscale level, this study contributes a novel analytical perspective and practical tools for understanding and improving the resilience of complex emergency coordination networks.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111732"},"PeriodicalIF":11.0,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158539","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

An efficient variance-based approach in RMDO framework of a space capsule under material and manufacturing uncertainties 材料和制造不确定条件下航天器RMDO框架的有效方差分析方法

IF 11 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-09-23 DOI: 10.1016/j.ress.2025.111751

Hassan Naseh, Hadiseh Karimaei, Mohammad Lesani Fadafan

{"title":"An efficient variance-based approach in RMDO framework of a space capsule under material and manufacturing uncertainties","authors":"Hassan Naseh, Hadiseh Karimaei, Mohammad Lesani Fadafan","doi":"10.1016/j.ress.2025.111751","DOIUrl":"10.1016/j.ress.2025.111751","url":null,"abstract":"<div><div>This paper presents an efficient variance-based Robust Multi-disciplinary Design Optimization (RMDO) framework aimed at minimizing the total mass of a re-entry space capsule under uncertainties, including manufacturing and assembly dimensional tolerances, as well as structural material properties (density, Young's modulus, Poisson's ratio). The method integrates an All-At-Once (AAO) approach within the MDO framework, utilizing a genetic algorithm optimizer. After finding an optimal design point, its robustness is evaluated. If the design is not robust, design constraints are adjusted to move away from the optimal boundary, and the MDO process is repeated until robustness criteria are satisfied. The robustness assessment begins by analyzing the correlation between objective functions and constraints through Design Of Experiment (DOE) using Latin hypercube sampling (LHS) to model input uncertainties. Surrogate Method (Kriging) is used to generate the objective function and constraints. The final step in the RMDO framework evaluates how input uncertainties affect the optimal design and constraints. Results show the RMDO-optimized capsule is 10.7 % lighter than the native version while maintaining safety and stability. Consequently, according to the variance-based RMDO evaluation, the critical constraint functions have at least a 2-sigma uncertainty-based margin of safety in the problem, which confirms the design's robustness.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111751"},"PeriodicalIF":11.0,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158507","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

Reliability analysis of tensile membrane structures using active learning-aided metamodeling 基于主动学习辅助元建模的拉伸膜结构可靠性分析

IF 11 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-09-23 DOI: 10.1016/j.ress.2025.111734

Ajmal Babu Mahasrankintakam , Siddhartha Ghosh , Allan L. Marbaniang , Sounak Kabasi

{"title":"Reliability analysis of tensile membrane structures using active learning-aided metamodeling","authors":"Ajmal Babu Mahasrankintakam , Siddhartha Ghosh , Allan L. Marbaniang , Sounak Kabasi","doi":"10.1016/j.ress.2025.111734","DOIUrl":"10.1016/j.ress.2025.111734","url":null,"abstract":"<div><div>The design and construction of tensile membrane structures (TMS) are undergoing standardization currently. Modern structural design is generally based on reliability analysis which assesses the structural performance under various limit states in a probabilistic sense. Traditional reliability methods work well for linear or mildly nonlinear systems, and are therefore unsuitable for the highly nonlinear TMS behavior. Probabilistic simulation methods provide a more robust framework for complex limit states, but are computationally prohibitive, besides the already computation-heavy form-finding and load analysis of TMS. To alleviate this computational burden, metamodeling techniques offer a surrogate for full-scale simulations. However, accurate metamodels often require a large number of training points, increasing the computational cost. This paper proposes the integration of active learning techniques into metamodeling by strategically choosing training points within the region of interest near the limit state, enabling a more accurate estimation of the reliability index, with fewer training samples compared to standard metamodeling methods. The proposed methodology is tested on diverse TMS shapes to demonstrate its effectiveness in evaluating their reliability for different (and complex) limit states. The results clearly demonstrate how the proposed approach achieves this with reduced computational costs and higher accuracy, compared to “conventional” approaches.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111734"},"PeriodicalIF":11.0,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158508","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

Choosing portfolios of reinforcement actions for distribution grids based on partial information 基于部分信息的配电网加固措施组合选择

IF 11 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-09-23 DOI: 10.1016/j.ress.2025.111729

Joaquín de la Barra , Ahti Salo , Mahdi Pourakbari-Kasmaei

{"title":"Choosing portfolios of reinforcement actions for distribution grids based on partial information","authors":"Joaquín de la Barra , Ahti Salo , Mahdi Pourakbari-Kasmaei","doi":"10.1016/j.ress.2025.111729","DOIUrl":"10.1016/j.ress.2025.111729","url":null,"abstract":"<div><div>The cost-efficiency of individual reinforcement actions in mitigating risks of external hazards in distribution grids depends on the entire portfolio of implemented actions. Thus, when seeking to reinforce distribution grids, it is pertinent to assess <em>portfolios</em> of reinforcement actions to account for dependencies between them. Motivated by this recognition, we develop a systemic framework to support Distribution System Operators (DSOs) in allocating scarce resources to portfolios of reinforcement actions that help protect multiple grids against hazards in the light of complementary reliability indices. This decision problem is structured as an influence diagram that contains scenarios representing combinations of realizations for different types of hazards. For cases where scenario probabilities, perceived importance of the grids, and relevance of reliability indices are known, the framework solves a mixed-integer linear programming problem to determine optimal portfolios. If this is not the case, the framework accommodates partial information about these parameters. Building on this partial information, it computes all the non-dominated portfolios by obtaining optimal portfolios for specific parameters and screening the other feasible portfolios. The non-dominated portfolios are analyzed to guide the choice of reinforcement actions at different budget levels. The framework is illustrated with a case study where the DSO seeks to mitigate risks associated with three types of hazards in three distribution grids. The novelty of the proposed optimization-based framework lies in (i) combining Portfolio Decision Analysis (PDA) and reliability models to determine cost-efficient reinforcement portfolios and (ii) accommodating partial information about parameters required by PDA and reliability models.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111729"},"PeriodicalIF":11.0,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158415","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

Cascading failure resilience of dual-layer supply chain networks under enterprise competition with incomplete information 企业不完全信息竞争下双层供应链网络的级联失效弹性

IF 11 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-09-23 DOI: 10.1016/j.ress.2025.111735

Xiuwen Fu , Mengyao Tian , Xiangwei Liu , Shaomin Wu , Rui Peng

{"title":"Cascading failure resilience of dual-layer supply chain networks under enterprise competition with incomplete information","authors":"Xiuwen Fu , Mengyao Tian , Xiangwei Liu , Shaomin Wu , Rui Peng","doi":"10.1016/j.ress.2025.111735","DOIUrl":"10.1016/j.ress.2025.111735","url":null,"abstract":"<div><div>Cascading failures are a critical factor affecting the operation of supply chain systems and have received widespread attention. In real-world cases, when an enterprise fails, resources are not evenly distributed to nearby similar enterprises. Instead, they are indirectly allocated through adjustments based on the competition and cooperation among enterprises. Moreover, enterprises often withhold complete information during competition in order to gain more benefits. These factors all influence cascading failures in supply chains. Therefore, we investigate the resilience of cascading failures in dual-layer supply chain networks under enterprise competition with incomplete information. We propose a supply-sales dual-layer network model that takes into account product similarity and enterprise competitiveness. Based on this model, we develop a cascading failure mechanism that includes node competition, replacement, and indirect neighboring load redistribution. Additionally, we incorporate the concept of enterprise information transparency to align with real-world supply chains. Experimental results indicate that (1) increased enterprise transparency can enhance the network’s resilience to cascading failures; (2) for suppliers, focusing on the quality rather than the quantity of cooperative sales enterprises is more critical for resisting cascading failures; (3) compared to the sales network, attacks on the supply network can result in a larger scale of cascading failures.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111735"},"PeriodicalIF":11.0,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158512","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

From flood-prone to flood-ready: The restoration-adaptation interplay in building resilient multimodal transport networks 从洪水易发到洪水准备：建设弹性多式联运网络中的恢复-适应相互作用

IF 11 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-09-23 DOI: 10.1016/j.ress.2025.111737

Chunhong Li , Bin Jia , Weiping Wang , Jianxi Gao , Albert Solé-Ribalta , Javier Borge-Holthoefer

{"title":"From flood-prone to flood-ready: The restoration-adaptation interplay in building resilient multimodal transport networks","authors":"Chunhong Li , Bin Jia , Weiping Wang , Jianxi Gao , Albert Solé-Ribalta , Javier Borge-Holthoefer","doi":"10.1016/j.ress.2025.111737","DOIUrl":"10.1016/j.ress.2025.111737","url":null,"abstract":"<div><div>Urban transport systems face escalating extreme weather risks due to global climate change. Following UN’s Sustainable Development Goals, building and fostering resilient urban transport systems — understood here not only as resilient against stress and shocks, but also prepared to adapt and transform to a changing environment — is imperative. Such objective faces, among others, two main difficulties: first, the increased complexity of entangled transportation layers, <em>i.e.</em>, multimodality, at the face of an event threatening its integrity. Second, the uncertainty of a vast number of travelers, whose reaction to a flooding event is driven by their own motivations and incentives. Here, we introduce an integrated framework to address both challenges, taking as a case study the city of Hamburg in Germany. Our thorough exploration provides insights spanning structural aspects — considering multiple restoration strategies — and behavioral ones—individual and collective transitions in response to floods. Beyond the larger success of one or another network restoration prioritization, results point at the intricate and subtle connection between network structure, traffic dynamics and population’s decisions. Thus, only a fine coordination of network restoration and timely information to guarantee travelers’ awareness can optimize the network functional recovery and foster the resilience against floods of the urban integrated transport system.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111737"},"PeriodicalIF":11.0,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158417","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

Dynamic flood risk modeling in urban metro systems considering station configuration 考虑车站配置的城市地铁系统动态洪水风险建模

IF 11 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-09-23 DOI: 10.1016/j.ress.2025.111760

Chen Liang , Mingfu Guan , Kaihua Guo , Dapeng Yu , Jie Yin

{"title":"Dynamic flood risk modeling in urban metro systems considering station configuration","authors":"Chen Liang , Mingfu Guan , Kaihua Guo , Dapeng Yu , Jie Yin","doi":"10.1016/j.ress.2025.111760","DOIUrl":"10.1016/j.ress.2025.111760","url":null,"abstract":"<div><div>Urban flooding poses a significant threat to the operational continuity and safety of metro systems. This study aimed to develop a spatiotemporally dynamic flood risk assessment framework for urban metro systems based on flood modeling. The framework was demonstrated through a case study of the extreme flooding triggered by a record-breaking rainstorm on September 7, 2023, in Hong Kong. A two-dimensional shallow water equations (2D-SWEs) based hydrodynamic model was employed to reproduce the extreme urban flooding, which agrees well with the observed inundation locations. The simulated grid-based inundation was then used to quantify spatiotemporal flood hazard posing to the metro system, with tailored criteria for aboveground, underground, and elevated metro stations. Exposure and vulnerability were assessed by analyzing the construction and operational characteristics of the metro system. By integrating flood hazard, exposure, and vulnerability maps, the spatiotemporal flood risk of Hong Kong's metro system during the historical extreme flood event was comprehensively assessed. In the case study, 46.4% of metro stations were exposed to high or very high flood hazards, while only 29.1% were classified as having high or greater overall flood risk. The temporal analysis further revealed that peak station risk occurred 1–12.5 h after peak rainfall, with an average lag of about 5 h. These findings demonstrate the effectiveness of the proposed framework in capturing the temporal and spatial variability of flood risk at the station scale, providing valuable insights for emergency preparedness and planning.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111760"},"PeriodicalIF":11.0,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158506","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

An integrated approach of knowledge-driven and neural network for fatigue remaining useful life prediction within small sample conditions 基于知识驱动和神经网络的小样本疲劳剩余使用寿命预测方法

IF 11 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-09-22 DOI: 10.1016/j.ress.2025.111752

Xiaoduo Fan , Jianguo Zhang , Xiaoqi Xiao

{"title":"An integrated approach of knowledge-driven and neural network for fatigue remaining useful life prediction within small sample conditions","authors":"Xiaoduo Fan , Jianguo Zhang , Xiaoqi Xiao","doi":"10.1016/j.ress.2025.111752","DOIUrl":"10.1016/j.ress.2025.111752","url":null,"abstract":"<div><div>Fatigue remaining useful life (RUL) prediction plays a vital role in improving the operational performance and reducing the failure risk of machinery through effective maintenance management. As a result, it has extracted increasing attention and is furtherly investigated within diverse industrial fields, wherein small sample condition poses to several challenges. Consequently, we propose an integrated fatigue RUL prediction approach based on the fusion of knowledge and neural network under small sample case. Specifically, the crack propagation mechanism is determined referring to correlated domain knowledge, and large scales of fault statistics are obtained via updated model firstly. Furthermore, a fusion approach based on multiple failure mechanisms is devised to generate pseudo-labeled fault data. Then, a three-stage pre-training model based on deep neural network oriented to RUL prediction is designed, wherein both generated and a few of experimental data are utilized fully. The proposed approach is implemented in a practical case study regarding an aircraft fuselage panel and the results demonstrate the enhancement in RUL prediction accuracy.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111752"},"PeriodicalIF":11.0,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145267743","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