{"title":"An optimal joint maintenance and mission abort policy for a system executing multi-attempt missions","authors":"Sangqi Zhao , Yian Wei , Yang Li , Yao Cheng","doi":"10.1016/j.ress.2025.111667","DOIUrl":"10.1016/j.ress.2025.111667","url":null,"abstract":"<div><div>Mission-critical systems are subject to deterioration-induced failures that induce not only mission failure cost but also system failure penalty. Deciding whether and when to abort the mission is crucial for overall cost minimization. When a mission’s success is evaluated in terms of the cumulative execution time and can be achieved by multiple attempts, operators can implement maintenance to increase the mission success probability. This calls upon the need to decide the system maintenance timing together with mission abort decisions, which is challenging due to not only the complex multi-layer interactions between these two decision variables but also the large state and action spaces. In this paper, we develop a Markov decision process (MDP) framework to determine the optimal system maintenance and mission abort timing. First, we propose a joint maintenance and mission abort policy that enables the operator to include the impact of the maintenance cost into decision-making and implement system maintenance and mission abort throughout the mission execution process, which thereby outperforms existing alternatives in overall cost minimization. Second, we develop an MDP-based optimization framework and analytically obtain the structural properties of the optimal policy, including the existence of the state-dependent control limits for system maintenance and mission abort decisions and their interdependence. Third, we develop an enhanced value iteration algorithm that exploits the developed structural properties to significantly improve the computational efficiency over the standard approach. The advantages of the proposed policy and algorithm are demonstrated by a case study of a UAV performing a surveillance mission.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111667"},"PeriodicalIF":11.0,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096838","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}
{"title":"Applicability of the TACOM measure as a tool to identify a high workload task in a proceduralized task environment","authors":"Jinkyun Park , Per Øivind Braarud","doi":"10.1016/j.ress.2025.111685","DOIUrl":"10.1016/j.ress.2025.111685","url":null,"abstract":"<div><div>One of the important requirements to ensure the sustainability of socio-technical systems such as nuclear power plants is to operate them as safely as possible. To this end, it is indispensable to identify and manage the critical factors that can affect their operational safety. As historical events strongly support the significance of human performance degradations (e.g., human errors) on the operational safety of socio-technical systems, the specification of tasks with the potential to result in high workload conditions is crucial for preventing the degradation of human performance. In this study, based on the TACOM (Task Complexity) measure, a novel framework is proposed with two distinctive rules that enables the identification of tasks that could give a high workload to human operators. In order to investigate the applicability of the proposed framework, a case study is carried out using performance data of human operators collected from a large-scale simulation study. As a result, in cases where operators have to accomplish required tasks described in a procedure (i.e., a proceduralized task environment), it seems to be positive to conclude that the proposed framework can be soundly used for identifying high workload tasks.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111685"},"PeriodicalIF":11.0,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145049608","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}
Gyeongho Kim , Jae Gyeong Choi , Sujin Jeon , Soyeon Park , Sunghoon Lim
{"title":"Towards efficient data-driven fault diagnosis under low-budget scenarios via hybrid deep active learning","authors":"Gyeongho Kim , Jae Gyeong Choi , Sujin Jeon , Soyeon Park , Sunghoon Lim","doi":"10.1016/j.ress.2025.111637","DOIUrl":"10.1016/j.ress.2025.111637","url":null,"abstract":"<div><div>Accurate fault diagnosis using deep learning (DL) has become essential for effective quality control, maintenance, and process automation in various industrial processes. However, an efficient labeling strategy is required because constructing large-scale labeled datasets to train DL-based predictive models entails considerable cost and labor. While active learning (AL) has been a prominent solution for efficient data labeling in fault diagnosis, existing AL approaches are unsuitable in practice due to low-budget scenarios where there is insufficient labeled data to train the model stably. In this regard, this work proposes a novel method, called a hybrid deep active learning for low-budget (HDAL-LB) scenarios, that addresses emerging challenges in the label-scarce regime to perform efficient fault diagnosis. First, self-supervised learning is performed with a deep stacked residual variational auto-encoder to efficiently initialize an encoder for latent feature extraction. Second, an evidential learning-based training technique is developed to enable a cost-efficient generation of calibrated predictive uncertainty. Third, a hybrid query selection is systematically formulated under a combinatorial optimization framework, utilizing both uncertainty and data diversity for deep AL. The efficacy of the proposed method (i.e., HDAL-LB) in fault diagnosis is validated through four case studies, utilizing three public benchmark datasets and one private real-world dataset. The comprehensive experimental results demonstrate the superior performance of HDAL-LB under low-budget scenarios compared to existing baseline and state-of-the-art (SOTA) AL methods. Furthermore, extensive ablation studies demonstrate that HDAL-LB consistently exhibits effective fault diagnosis performance across various experimental settings, highlighting its label efficiency and practical applicability in real-world practice.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111637"},"PeriodicalIF":11.0,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145027141","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}
Jiawei Gu , Xiangxiang Yuan , Xinming Li , Yanxue Wang , Jinduo Xing
{"title":"Symmetric Radial Vectors for uncertainty-aware rotary machinery fault diagnosis","authors":"Jiawei Gu , Xiangxiang Yuan , Xinming Li , Yanxue Wang , Jinduo Xing","doi":"10.1016/j.ress.2025.111639","DOIUrl":"10.1016/j.ress.2025.111639","url":null,"abstract":"<div><div>Rotary machinery fault diagnosis faces persistent challenges in handling class imbalance, adapting to evolving fault patterns, and quantifying diagnostic uncertainty. Traditional deep learning approaches often struggle with these issues, particularly when dealing with a large number of fault categories or limited samples for rare fault types. This paper introduces a novel fault diagnosis framework based on Symmetric Radial Vectors (SRVs), specifically designed to address these technical hurdles. Our method predefines fixed, normalized vector embeddings for each fault type, serving as stable reference points in the feature space. By minimizing the spherical distance between input feature embeddings and their corresponding fault-type SRVs, we achieve robust classification even with imbalanced datasets. The predefined nature of SRVs allows for efficient handling of numerous fault categories without increasing model complexity, crucial for comprehensive fault coverage. Furthermore, the geometric properties of SRVs enable natural uncertainty quantification, as the distances to different fault-type vectors provide a direct measure of diagnostic confidence. We demonstrate the efficacy of our approach on benchmark datasets of rotary machinery faults, showing improved accuracy for rare fault classes and well-calibrated uncertainty estimates. Our method also exhibits strong adaptability to newly emerging fault types, a critical feature for evolving industrial systems.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111639"},"PeriodicalIF":11.0,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145027142","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}
{"title":"Probabilistic risk assessment for inert gas system on oil tanker ships using system theoretic accident model and process (STAMP) and Bayesian belief network (BBN)","authors":"Bulut Ozan Ceylan , Gizem Elidolu , Sukru Ilke Sezer , Emre Akyuz , Zaili Yang","doi":"10.1016/j.ress.2025.111669","DOIUrl":"10.1016/j.ress.2025.111669","url":null,"abstract":"<div><div>As shipboard systems increasingly prioritize automation over human intervention, risk assessment models must adapt to this paradigm shift. The proposed framework addresses this need by focusing on software, hardware, and external factors including human factors, aligning with modern technological dependencies. This research conducts an extensive risk analysis of the inert gas system (IGS) on oil tankers by adopting system theoretic accident model and process (STAMP) and Bayesian belief network (BBN). While the STAMP identifies failure scenarios through a hierarchical control and feedback structure, BBN quantifies the failure probabilities based on STAMP outcomes. The study identifies critical failure pathways through STAMP’s systemic hazard analysis and BBN’s probabilistic quantification and calculates the system failure probability as 1.29E-01. The results indicate that the most critical failures in IGS are “Flame instability or burner failure”, “Inert gas blower fan failure”, and “Insufficient pressure during operation” from the hardware component. The methodology enhances predictive accuracy and provides actionable strategies for mitigating risks in increasingly automated maritime operations. The research outcomes are expected to provide valuable insights for maritime safety managers, safety inspectors, technical inspectors, HSEQ managers, and ship crews to improve operational safety as well as prevent potential risks for inert gas incidents on-board oil tankers.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111669"},"PeriodicalIF":11.0,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145267754","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}
{"title":"Transfer learning from physical scale information: A signal identification method for mine system security monitoring","authors":"Linqi Huang, Wanjie Liu, Xibing Li, Zhaowei Wang","doi":"10.1016/j.ress.2025.111665","DOIUrl":"10.1016/j.ress.2025.111665","url":null,"abstract":"<div><div>Earthquake signals and microseismic signals are elastic waves excited by the sudden release of energy inside the geological medium, but they differ in the scale of their respective seismic sources. This makes it possible to learn from physical information at different scales. We proposed a one-dimensional convolutional neural network under transfer learning framework to learn how to identify microseismic signals using the discrimination of earthquake magnitude. We first trained the convolutional neural network using numerous labeled seismic signal data and then fine-tuned the partial weights using a small amount of microseismic data. Experimental results demonstrate the classification results on the microseismic database are as high as 100 %. When the number of samples is reduced to 100 signals, the model can still maintain a minimum accuracy of 96 % on the same dataset. When the signal-to-noise ratio gradually increases to 0dB, the minimum accuracy of the model reaches 95.35 %. Compared with traditional machine learning (SVM, Logistic Regression, Naive Bayes), the accuracy of the model increased by 6.19 %, 16.00 % and 40.30 % respectively. The research result above show the model has excellent classification accuracy and high robustness, providing better pre-technical support for the safety and stability of mine systems.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111665"},"PeriodicalIF":11.0,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096772","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}
{"title":"Multi-objective optimization for pipeline systems: A maintenance model using NSGA-II considering flow capacity and total cost","authors":"Mingjiang Xie , Jie Li , Ziqi Wei , Guanghan Bai","doi":"10.1016/j.ress.2025.111663","DOIUrl":"10.1016/j.ress.2025.111663","url":null,"abstract":"<div><div>The maintenance of corroded pipelines poses a significant challenge to ensuring operational safety and efficiency. Effective maintenance strategies must consider various performance metrics with multiple competing objectives. A key issue in optimizing these maintenance strategies is balancing maintenance costs with flow rates. This paper addresses the maintenance challenges of complex pipeline systems affected by corrosion by establishing a multi-objective optimization model, which considers both maintenance costs and system flow rates as optimization objectives. A novel chromosome encoding method is proposed to solve the model using the non-dominated sorting genetic algorithm-II (NSGA II). Compared to traditional empirical strategies, the strategies developed through the proposed multi-objective optimization method reduce total costs by 1.84 %–7.25 % and improve system delivery flow rates by 1.07 %–15.33 %. The effectiveness and universality of the proposed method are demonstrated through case studies of three pipeline systems with different structural complexities, failure probability thresholds and corrosion degradation models. Finally, comparative analyses with other multi-objective optimization methods (SPEA2, PESA-II, MOPSO, and MOEA/D) and sensitivity analyses show that the proposed NSGA II-based strategy exhibits superior performance in terms of convergence and effectiveness.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111663"},"PeriodicalIF":11.0,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145020844","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}
Pu Cheng , Yuchen Cai , Jie Zhong , Zhiqiang Xu , Qiang Miao
{"title":"Parallel time-series mixer network enhanced by slicing procedure and attention mechanism for remaining useful life prediction","authors":"Pu Cheng , Yuchen Cai , Jie Zhong , Zhiqiang Xu , Qiang Miao","doi":"10.1016/j.ress.2025.111635","DOIUrl":"10.1016/j.ress.2025.111635","url":null,"abstract":"<div><div>The prediction of an aero-engine’s Remaining Useful Life (RUL) is a critical task in Prognostics and Health Management (PHM). While deep learning has shown promise, existing models often struggle with the variable-length time-series sequences common in aero-engine monitoring and fail to effectively capture complex temporal patterns and cross-variate information. This paper presents an advanced approach for predicting the RUL of aero-engines through the proposal of the CoSO-pTSMixer-SGA network. The network includes three key blocks: the Concentrating and Slicing Operator (CoSO), the parallel Time-Series Mixer (pTSMixer), and the Scalable Global Attention (SGA), designed to handle variable-length data flexibly and enhance feature extraction. Extensive experiments on the C-MAPSS dataset demonstrate that CoSO-pTSMixer-SGA achieves state-of-the-art performance, with a 6.4% reduction in RMSE and a 3.4% reduction in Score compared to other leading methods. The network is particularly effective under complex operating conditions, outperforming others by up to 10.4% in key datasets’ RMSE. Ablation studies validate the contributions of each element, and a novel RMSE-60 metric is introduced for a more targeted evaluation. The CoSO-pTSMixer-SGA network offers a flexible and precise solution for real-world RUL estimation tasks.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111635"},"PeriodicalIF":11.0,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145060872","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}
{"title":"A novel method for reliability design of multi-tier circular (k,Smin)-out-of-(n1,…,nm,S): G balanced systems subject to external disturbances","authors":"Bingchen Dong, Zhenglin Liang","doi":"10.1016/j.ress.2025.111621","DOIUrl":"10.1016/j.ress.2025.111621","url":null,"abstract":"<div><div>Balanced systems composed of spatially distributed components are critical to numerous industrial technologies, such as reusable launch vehicles. However, balancing systems with multi-tier circular configurations subjected to stochastic component failures and potential omnidirectional disturbances presents challenges. This study proposes a novel multi-tier circular (<span><math><mrow><mi>k</mi><mo>,</mo><msub><mrow><mi>S</mi></mrow><mrow><mi>m</mi><mi>i</mi><mi>n</mi></mrow></msub></mrow></math></span>)-out-of-(<span><math><mrow><msub><mrow><mi>n</mi></mrow><mrow><mn>1</mn></mrow></msub><mo>,</mo><mo>…</mo><mo>,</mo><msub><mrow><mi>n</mi></mrow><mrow><mi>m</mi></mrow></msub><mo>,</mo><mi>S</mi></mrow></math></span>): G balanced model, accounting for stochastic omnidirectional disturbances. The model features components across concentric tiers, each with controllable thrust to coordinately counteract disturbances. Subsequently, a new methodology based on system resilience coverage area is proposed for evaluating its balancing capability, where sufficient balance is ensured if the operational components form a resilience coverage area above a threshold. Furthermore, a rebalancing mechanism is developed by adjusting angular offsets across tiers to enlarge this area. A percolation-based method is then applied to analyze system reliability transitions and optimize redundancy design. Finally, numerical experiments are conducted for scenarios with and without the proposed rebalancing mechanism. Results demonstrate the significant effectiveness of the mechanism in reducing failure modes and enhancing reliability. Moreover, practical design guidelines are summarized to support system redundancy optimization. This research advances the <span><math><mi>k</mi></math></span>-out-of-<span><math><mi>n</mi></math></span> system framework and offers valuable guidance for reliability analysis and design in related systems.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111621"},"PeriodicalIF":11.0,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145005231","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}
Kun Zhang , Jiayi Fan , Miaorui Yang , Hong Jiang , Yonggang Xu
{"title":"Harmonic Fourier decomposition and its application in fault identification of rotating machinery system","authors":"Kun Zhang , Jiayi Fan , Miaorui Yang , Hong Jiang , Yonggang Xu","doi":"10.1016/j.ress.2025.111657","DOIUrl":"10.1016/j.ress.2025.111657","url":null,"abstract":"<div><div>As one of the most failure-prone critical components in rotating machinery, rolling bearings generate fault signatures exhibiting energy concentration in spectral distributions, thereby offering significant opportunities for deploying one-dimensional signal decomposition techniques in condition monitoring applications. To address the enduring challenge of weak fault feature extraction in practical bearing diagnostics, this study proposes a Harmonic Fourier Decomposition (HFD) framework. The methodology derives mode boundaries through Fourier trend analysis of power spectral density (PSD), effectively reducing computational complexity and eliminating spurious components. A zero-phase Fourier filter bank is employed for frequency-band segmentation, achieving simultaneous minimization of spectral leakage and enhancement of computational efficiency. Furthermore, Harmonic Spectral Kurtosis (HSK) is innovatively integrated to quantify cyclostationary impulse components while suppressing transient interference and background noise. Experimental validation using both simulated signals and bearing test-rig data confirms the method's capability to reliably identify localized defects in inner raceways and outer raceways.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"266 ","pages":"Article 111657"},"PeriodicalIF":11.0,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145049605","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}