Reliability Engineering & System Safety最新文献_第4页

Quantitative analysis of risk propagation in urban rail transit: A novel ensemble learning method based on the structure of Bayesian Network 城市轨道交通风险传播定量分析：一种基于贝叶斯网络结构的集成学习方法

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-22 DOI: 10.1016/j.ress.2025.111280

Yuanxi Xu, Keping Li, Yanyan Liu

{"title":"Quantitative analysis of risk propagation in urban rail transit: A novel ensemble learning method based on the structure of Bayesian Network","authors":"Yuanxi Xu, Keping Li, Yanyan Liu","doi":"10.1016/j.ress.2025.111280","DOIUrl":"10.1016/j.ress.2025.111280","url":null,"abstract":"<div><div>The quantification of risk propagation in urban rail transit systems is a critical task to ensure the safe operations. In this study, a novel ensemble learning method based on Bayesian network structure learning is developed to describe the risk propagation mechanisms. The proposed model addresses the reliance problem on ordering and is capable to quantify more complex risk propagation paths. First, an information-based criterion and a score function are proposed to construct the initial propagation structure. Second, a structure constructing algorithm is introduced to generate multiple Bayesian networks, forming a Bayesian Forest. Finally, three applications of the Bayesian Forest are introduced: scenario inference, sensitivity analysis and risk propagation chain evaluation. Additionally, a case study is made on the application of the proposed model to the Shanghai metro system to verify its effectiveness. The results validate the rationality of the ensemble learning method by analyzing multiple risk propagation paths. The interaction characteristics are explicitly described by sensitivity of risk factors and the significance of the risk propagation chain is accurately evaluated.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"263 ","pages":"Article 111280"},"PeriodicalIF":9.4,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144147879","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

Mixed shock model for the multi-state system with a two-phase degradation process under Markov environment 马尔可夫环境下具有两阶段退化过程的多态系统混合激波模型

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-22 DOI: 10.1016/j.ress.2025.111254

Hao Lyu , Hengxin Wei , Hualong Xie , Yimin Zhang

{"title":"Mixed shock model for the multi-state system with a two-phase degradation process under Markov environment","authors":"Hao Lyu , Hengxin Wei , Hualong Xie , Yimin Zhang","doi":"10.1016/j.ress.2025.111254","DOIUrl":"10.1016/j.ress.2025.111254","url":null,"abstract":"<div><div>Reliability analysis of multi-state systems is crucial in engineering, particularly when dependent competing failure processes arise from both degradation and shocks. Many existing models do not fully capture the dependencies between shock processes and their influence on system deterioration. This study develops a mixed shock model under a Markov environment, integrating a two-phase degradation process. The shock processes are characterized using a Poisson phase-type process, which accounts for dependencies in damage increments. System states evolve through distinct functional levels: perfect function, degraded function, and severely degraded function. Soft failure occurs when cumulative degradation exceeds a predefined threshold, whereas hard failure results from extreme shocks or the accumulation of damage. By employing the finite Markov chain imbedding approach and phase-type distribution, explicit reliability functions are formulated. A case study on a spool valve validates the model, demonstrating its applicability in evaluating the reliability of multi-state systems. The proposed model provides an enhanced framework for assessing the reliability of complex engineering systems, addressing dependencies in degradation and shock processes.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"264 ","pages":"Article 111254"},"PeriodicalIF":9.4,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144190021","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

Explainable AI guided unsupervised fault diagnostics for high-voltage circuit breakers 可解释的AI引导高压断路器无监督故障诊断

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-22 DOI: 10.1016/j.ress.2025.111199

Chi-Ching Hsu , Gaëtan Frusque , Florent Forest , Felipe Macedo , Christian M. Franck , Olga Fink

{"title":"Explainable AI guided unsupervised fault diagnostics for high-voltage circuit breakers","authors":"Chi-Ching Hsu , Gaëtan Frusque , Florent Forest , Felipe Macedo , Christian M. Franck , Olga Fink","doi":"10.1016/j.ress.2025.111199","DOIUrl":"10.1016/j.ress.2025.111199","url":null,"abstract":"<div><div>Commercial high-voltage circuit breaker (CB) condition monitoring systems rely on directly observable physical parameters such as gas filling pressure with pre-defined thresholds. While these parameters are crucial, they only cover a small subset of malfunctioning mechanisms and usually can be monitored only if the CB is disconnected from the grid. To facilitate online condition monitoring while CBs remain connected, non-intrusive measurement techniques such as vibration or acoustic signals are necessary. Currently, CB condition monitoring studies using these signals typically utilize supervised methods for fault diagnostics, where ground-truth fault types are known due to artificially introduced faults in laboratory settings. This supervised approach is however not feasible in real-world applications, where fault labels are unavailable. In this work, we propose a novel unsupervised fault detection and segmentation framework for CBs based on vibration and acoustic signals. This framework can detect deviations from the healthy state. The explainable artificial intelligence (XAI) approach is applied to the detected faults for fault diagnostics. The specific contributions are: (1) we propose an integrated unsupervised fault detection and segmentation framework that is capable of detecting faults and clustering different faults with only healthy data required during training (2) we provide an unsupervised explainability-guided fault diagnostics approach using XAI to offer domain experts potential indications of the aged or faulty components, achieving fault diagnostics without the prerequisite of ground-truth fault labels. These contributions are validated using an experimental dataset from a high-voltage CB under healthy and artificially introduced fault conditions, contributing to more reliable CB system operation.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"263 ","pages":"Article 111199"},"PeriodicalIF":9.4,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144135158","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

Bi-objective redundancy allocation problem in systems with mixed strategy: NSGA-II with a novel initialization 混合策略系统的双目标冗余分配问题：具有新初始化的NSGA-II

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-22 DOI: 10.1016/j.ress.2025.111279

Mateusz Oszczypała

{"title":"Bi-objective redundancy allocation problem in systems with mixed strategy: NSGA-II with a novel initialization","authors":"Mateusz Oszczypała","doi":"10.1016/j.ress.2025.111279","DOIUrl":"10.1016/j.ress.2025.111279","url":null,"abstract":"<div><div>The redundancy allocation problem (RAP) aims to maximize system availability while minimizing costs, subject to weight constraints. The solution to the bi-objective RAP is represented by a Pareto front, comprising non-dominated system configurations. Previous studies have focuses on refining processes such as dominance relationship determination, selection, crossover, and mutation. This paper enhances the Non-dominated Sorting Genetic Algorithm-II (NSGA-II) by introducing a novel approach for generating the initial population. While genetic algorithms traditionally rely on random population generation, this work proposes Scaled Binomial Initialization (SBI), which adjusts the probability of generating binary numbers for subsequent individuals in the initial population. SBI improves the diversity of chromosomes encoding component allocation priorities within subsystems, resulting in greater solution dispersion in the search space and enhanced exploration of regions with extreme objective function values. SBI is specifically designed for indirect chromosome encoding, ensuring feasible solutions across the population in all generations, thereby eliminating the need for a penalty function. A continuous-time Markov chain was developed to estimate the availability of k-out-of-n subsystems with a mixed redundancy strategy. The proposed method was evaluated on four benchmarks: a series system, a series-parallel system, a complex bridge system, and a large-scale system. For small-scale systems, NSGA-II with both random initialization and SBI achieved comparable levels of effectiveness and diversity in the Pareto front. However, for large-scale systems, NSGA-II with SBI demonstrated significant advantages, as reflected in the performance metrics of the approximated Pareto front.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"263 ","pages":"Article 111279"},"PeriodicalIF":9.4,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144184887","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

Time-to-failure based deterioration factors of water networks: Systematic review and prioritization 基于失效时间的水网退化因素：系统审查和优先排序

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-21 DOI: 10.1016/j.ress.2025.111246

Beenish Bakhtawar , Tarek Zayed , Nehal Elshaboury

{"title":"Time-to-failure based deterioration factors of water networks: Systematic review and prioritization","authors":"Beenish Bakhtawar , Tarek Zayed , Nehal Elshaboury","doi":"10.1016/j.ress.2025.111246","DOIUrl":"10.1016/j.ress.2025.111246","url":null,"abstract":"<div><div>Amidst global scarcity, preventing pipeline failures in water distribution systems is crucial for maintaining a clean supply while conserving water resources. Numerous studies have modelled water pipeline deterioration; however, existing literature does not correctly understand the failure time prediction for individual water pipelines. Existing time-to-failure prediction models rely on available data, failing to provide insight into factors affecting a pipeline's remaining age until a break or leak occurs. The study systematically reviews factors influencing time-to-failure, prioritizes them using a magnitude-based fuzzy analytical hierarchy process, and compares results with expert opinion using an in-person Delphi survey. The final pipe-related prioritized failure factors include <em>pipe geometry, material type, operating pressure, pipe age, failure history, pipeline installation, internal pressure, earth</em> and <em>traffic loads</em>. The prioritized environment-related factors include <em>soil properties, water quality, extreme weather events, temperature,</em> and <em>precipitation</em>. Overall, this prioritization can assist practitioners and researchers in selecting features for time-based deterioration modelling. Effective time-to-failure deterioration modelling of water pipelines can create a more sustainable water infrastructure management protocol, enhancing decision-making for repair and rehabilitation. Such a system can significantly reduce non-revenue water and mitigate the socio-environmental impacts of pipeline ageing and damage.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"263 ","pages":"Article 111246"},"PeriodicalIF":9.4,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144167599","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

Attention-guided graph isomorphism learning: A multi-task framework for fault diagnosis and remaining useful life prediction 注意引导图同构学习：故障诊断和剩余使用寿命预测的多任务框架

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-21 DOI: 10.1016/j.ress.2025.111209

Junyu Qi , Zhuyun Chen , Yun Kong , Wu Qin , Yi Qin

{"title":"Attention-guided graph isomorphism learning: A multi-task framework for fault diagnosis and remaining useful life prediction","authors":"Junyu Qi , Zhuyun Chen , Yun Kong , Wu Qin , Yi Qin","doi":"10.1016/j.ress.2025.111209","DOIUrl":"10.1016/j.ress.2025.111209","url":null,"abstract":"<div><div>Intelligent fault diagnosis and remaining useful life (RUL) prediction are essential for the reliable operation of rotating machinery. These technologies enhance safety, availability, and productivity in the manufacturing industry. Graph Convolutional Networks (GCNs), an extension of deep learning (DL) to graph data, provide superior performance due to their unique data representation capabilities. Traditional condition monitoring (CM) typically requires separate models for fault diagnosis and RUL prediction, leading to challenges such as ineffective knowledge sharing and high costs associated with preparing and deploying DL models. To address these issues, this study proposes a multi-task graph isomorphism network with an attention mechanism for simultaneous fault diagnosis and RUL prediction. This method considers the interrelationship between tasks, introducing both a parameter-sharing mechanism and a self-attention mechanism. Compared to traditional single-task methods, the proposed approach offers higher accuracy, greater practicality, and reduced costs of developing the model. The effectiveness of the method is validated using experimental degradation data, demonstrating its capability to address key issues in fault diagnosis and RUL prediction, exhibiting strong potential in practical applications.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"263 ","pages":"Article 111209"},"PeriodicalIF":9.4,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144135159","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

Modelling integrated inventory, maintenance and nonconforming output management of imperfect deteriorating production systems 对不完善恶化生产系统的综合库存、维护和不合格品输出管理进行建模

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-21 DOI: 10.1016/j.ress.2025.111273

Spyros I. Vlastos , Stratos Ioannidis , Dimitrios E. Koulouriotis

{"title":"Modelling integrated inventory, maintenance and nonconforming output management of imperfect deteriorating production systems","authors":"Spyros I. Vlastos , Stratos Ioannidis , Dimitrios E. Koulouriotis","doi":"10.1016/j.ress.2025.111273","DOIUrl":"10.1016/j.ress.2025.111273","url":null,"abstract":"<div><div>The advancement of knowledge concerning optimal practices in production systems management necessitates the continual development of comprehensive models, approximating real-world conditions. This study aims to contribute towards modelling and analysis of the decision parameters that govern the management of gradually deteriorating imperfect production systems. The integration of demand parameters represents an intriguing avenue for investigation, offering a comparative perspective on the efficacy of these parameters on nonconforming outcome management. Operating production equipment is subject to gradual deterioration, ultimately leading to complete failure. A condition-based maintenance policy, based on inspections, governed by a specific maintenance threshold correlated with the deterioration level, is employed. Depending on its extent, deterioration negatively affects the percentage of nonconforming parts produced. Moreover, nonconforming parts management policies, such as merchandising under varying demand conditions or reprocessing of such parts are investigated. Systems operation modelling is facilitated through continuous-time Markov chains. Execution of numerical experiments reveals the behavior of performance metrics while alternating system parameters. Concurrently, these experiments demonstrate the impact of implementing a specific management policy. It is pointed out that unilaterally optimizing a single key performance indicator may not always enhance the overall result.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"263 ","pages":"Article 111273"},"PeriodicalIF":9.4,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144167598","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

Maintenance strategies for a queueing system with a standby equipment: An integrated approach using condition-based monitoring 具有备用设备的排队系统的维护策略：使用基于状态的监测的集成方法

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-21 DOI: 10.1016/j.ress.2025.111219

Zeyu Luo , Zhaotong Lian , Jin Li , Zhixin Yang

{"title":"Maintenance strategies for a queueing system with a standby equipment: An integrated approach using condition-based monitoring","authors":"Zeyu Luo , Zhaotong Lian , Jin Li , Zhixin Yang","doi":"10.1016/j.ress.2025.111219","DOIUrl":"10.1016/j.ress.2025.111219","url":null,"abstract":"<div><div>This paper presents a comprehensive maintenance strategy for service systems by integrating condition-based maintenance (CBM) with queueing theory. The proposed strategy leverages real-time deterioration data to optimize server performance and reliability while balancing the costs of maintaining standby equipment and ordering new components. Our study develops an integrated maintenance model based on an M/M/1 queueing system, simulating performance degradation using condition monitoring data. This model determines the optimal reordering state for critical server equipment. Extensive numerical analyses validate its effectiveness, and a sensitivity analysis identifies key factors affecting cost and profitability. Key contributions include: (1) An integrated system model combining CBM and queueing theory to optimize maintenance strategies; (2) A computationally efficient Markov chain-based model that reduces complexity while maintaining accuracy; (3) Explicit formulas for performance metrics such as server availability, system reliability, and reorder lead time. The proposed model minimizes long-term average costs while maintaining high service availability and reliability, offering practical insights for improving maintenance efficiency across industries.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"263 ","pages":"Article 111219"},"PeriodicalIF":9.4,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144135084","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 and emergency maintenance strategy optimization of the multi-state airborne power supply system based on dependent competitive importance measure 基于依存竞争重要性测度的多状态机载供电系统可靠性分析及应急维护策略优化

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-20 DOI: 10.1016/j.ress.2025.111274

Yongfeng Jing , Jian Jiao , Yuan Yuan , Zhiwei Chen , Chen Lu , Hongyan Dui

{"title":"Reliability analysis and emergency maintenance strategy optimization of the multi-state airborne power supply system based on dependent competitive importance measure","authors":"Yongfeng Jing , Jian Jiao , Yuan Yuan , Zhiwei Chen , Chen Lu , Hongyan Dui","doi":"10.1016/j.ress.2025.111274","DOIUrl":"10.1016/j.ress.2025.111274","url":null,"abstract":"<div><div>The airborne power supply system provides reliable and stable power supply for airborne equipment, and its performance directly impacts mission success and flight safety. However, the airborne power supply system faces numerous challenges, particularly from environmental interference and internal components ageing, which create significant effects on maintaining stable operation during flights. Due to these complex factors, reliability analysis and optimization of emergency maintenance strategies for the system is difficult and rarely studied. In this paper, we propose a multi-state system reliability analysis and emergency maintenance strategy optimization method based on the dependent competing importance measure (DCIM). Firstly, a dependent competing failure process model with variable degradation rates is established to address the dynamic evolution of component states. Secondly, a system reliability analysis model based on the dependent competing failure process model and the semi-Markov process is developed to improve the accuracy of reliability assessment. Thirdly, the emergency maintenance strategy based on the DCIM is proposed and optimized under budgetary constraints. Finally, an airborne power supply system serves as case study to validate the efficacy of the proposed method and provide practical guidance for emergency maintenance decisions in similar applications.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"263 ","pages":"Article 111274"},"PeriodicalIF":9.4,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144135162","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

Adaptive frequency attention-based interpretable Transformer network for few-shot fault diagnosis of rolling bearings 基于自适应频率关注的可解释变压器网络在滚动轴承小故障诊断中的应用

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-20 DOI: 10.1016/j.ress.2025.111271

Keying Liu , Yifan Li , Zhaoyang Cui , Guangdong Qi , Biao Wang

{"title":"Adaptive frequency attention-based interpretable Transformer network for few-shot fault diagnosis of rolling bearings","authors":"Keying Liu , Yifan Li , Zhaoyang Cui , Guangdong Qi , Biao Wang","doi":"10.1016/j.ress.2025.111271","DOIUrl":"10.1016/j.ress.2025.111271","url":null,"abstract":"<div><div>In recent years, deep learning-based approaches have demonstrated superior performance in few-shot fault diagnosis. Nevertheless, many of these methods lack explicit interpretability, making it difficult to intuitively understand their diagnostic logic. To tackle this issue, an interpretable deep learning model called the adaptive frequency attention-based interpretable Transformer network is proposed for few-shot fault diagnosis of rolling bearings. From a frequency interpretability perspective, the standard Transformer network architecture has been innovatively improved. First, an adaptive frequency attention mechanism is developed that quantifies the importance of various frequency components during the diagnostic process, adaptively identifying and emphasizing key frequency components closely associated with fault modes. This boosts both diagnostic performance and model interpretability. Second, to enhance the diversity of fault features under limited sample conditions, a multiscale convolutional architecture is developed to replace the linear projection layer in input embedding. This architecture employs parallel multiscale convolution kernels to extract both local and global fault features, enabling a comprehensive capture of fault information and further supporting the interpretability of the diagnostic model. Finally, Experiments on interpretable few-shot fault diagnosis are carried out on three rolling bearing datasets, and the diagnostic results further validate the effectiveness and interpretability of the proposed method.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"263 ","pages":"Article 111271"},"PeriodicalIF":9.4,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144139430","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