Zhan Gao , Chengjie Wang , Jun Wu , Yuanhang Wang , Weixiong Jiang , Tianjiao Dai
{"title":"Degradation-Aware Remaining Useful Life Prediction of Industrial Robot via Multiscale Temporal Memory Transformer Framework","authors":"Zhan Gao , Chengjie Wang , Jun Wu , Yuanhang Wang , Weixiong Jiang , Tianjiao Dai","doi":"10.1016/j.ress.2025.111176","DOIUrl":"10.1016/j.ress.2025.111176","url":null,"abstract":"<div><div>Remaining useful life (RUL) prediction is of great importance to ensure stable operation of industrial robots (IRs). Deep learning-based methods have been proven effective in the RUL prediction tasks of IR. However, they are not effective in perceiving the state variation from a health state to a degradation state of IR and fail to reveal multi-term patterns of IR for RUL prediction. To address these challenges, a multiscale temporal memory Transformer framework is proposed to implement RUL prediction combined with state change identification. This proposed framework comprises a memory autoencoder Transformer network and a multiscale temporal Transformer network. The former Transformer network captures variation hidden in temporal information to detect the state change point, while the latter Transformer network is adopted to mine multi-term temporal dependencies for RUL prediction once state change point is identified. A self-built IR platform is constructed to validate our proposed method. Compared with the other advanced methods, the prediction results show that our method can locate the state change point in advance and achieve high-precision RUL prediction for IRs.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"262 ","pages":"Article 111176"},"PeriodicalIF":9.4,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143895356","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":"Improved identification of maritime risk-influencing factors using AIS data in regression analysis","authors":"Spencer August Dugan, Ingrid Bouwer Utne","doi":"10.1016/j.ress.2025.111156","DOIUrl":"10.1016/j.ress.2025.111156","url":null,"abstract":"<div><div>Understanding risk-influencing factors (RIFs) associated with the occurrence of maritime accidents is important to prevent their future occurrence, identify high-risk ships, and properly influence policy. However, current methods often suffer from selection bias or do not account for variations in ship exposure, leading to biased or incomplete assessments. This study addresses these gaps by incorporating AIS-derived activity metrics as offset variables in regression analysis. This transformation of the dependent variable leads to the analysis of accident rates. The method is applied to ship losses of command (i.e., loss of propulsion, loss of electrical power, or loss of directional control / steering) by cargo ships in Norwegian waters from 2017 to 2021. Significant variables influencing the rate of loss of command include ship’s flag state, ship manager domicile, number of inspection deficiencies, propulsion redundancy, and the use of a single fuel onboard. Inspection deficiencies and sailing with a flag of convenience are associated with increased rates. Sailing with a Norwegian ship manager, propulsion redundancy, and a single fuel type onboard are associated with decreased rates. Incorporating measures of ship activity as exposure significantly improves the overall model fit, leading to better identification of RIFs associated with the occurrence of ship losses of command. Sensitivity analyses using sailed distance as exposure and the Cox proportional hazards model demonstrate overall robustness. The results are beneficial for identifying high-risk ships from the perspective of vessel traffic management and can be used for decision-making. The method has promising potential for the future analysis of RIFs associated with other types of maritime accidents.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"262 ","pages":"Article 111156"},"PeriodicalIF":9.4,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143887349","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":"Functionality assessment of natural gas distribution networks in post-earthquake scenarios with widespread component failures","authors":"Heran Wang, Changhai Zhai, Liyang Ma, Dongdong Song, Lili Xie","doi":"10.1016/j.ress.2025.111134","DOIUrl":"10.1016/j.ress.2025.111134","url":null,"abstract":"<div><div>Urban natural gas distribution networks are critical infrastructure systems that provide essential energy services to residential, industrial, and commercial sectors. However, these networks are highly vulnerable to earthquake-induced damage, leading to significant functionality loss and risks such as fires and explosions. To evaluate the functional status of natural gas pipeline networks under post-earthquake conditions, it is essential to develop a robust evaluation model capable of addressing large-scale component damage. This study proposes a natural gas pipeline network functionality assessment methodology that integrates islanding analysis to identify interconnected sub-networks, pressure-dependent demand modeling for user nodes, and a dual-control mechanism for gas source nodes to improve the accuracy of hydraulic calculations under accident conditions. Compared to traditional methods, the proposed approach provides a more accurate representation of natural gas pipeline network behavior under partial gas supply conditions. Validation on a representative natural gas pipeline network demonstrates its effectiveness in identifying and quantifying functional losses during extensive component failures. Comparative analysis reveals that traditional methods tend to overestimate network functionality under severe damage conditions, underscoring the advantages of the proposed approach. These findings confirm the methodology’s suitability for evaluating functionality in scenarios of severe disruption.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"262 ","pages":"Article 111134"},"PeriodicalIF":9.4,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143899665","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":"Joint optimization of production loading and maintenance for production-storage systems","authors":"Jianyu Liang , Xiaohong Zhang , Jianchao Zeng , Guannan Shi , Huifang Niu","doi":"10.1016/j.ress.2025.111182","DOIUrl":"10.1016/j.ress.2025.111182","url":null,"abstract":"<div><div>Production-storage systems with adjustable loads are widely used in industrial production applications; however, system failures will affect mission success probability (MSP). Most existing studies on optimal production loading for such systems normally focus on the effects of maintenance activities conducted after production system failures. By incorporating preventive maintenance (PM) activities into the production optimization process, sudden failures can be avoided, thereby enhancing the MSP. To address this challenge above problems, this study proposes a joint optimization strategy for production loading and PM to maximize the system MSP. At any decision-making point, the optimal PM schedule and load level for the next production cycle are determined based on the amount of product in storage. A mathematical model was developed to calculate the MSP while considering the effects of PM. The proposed strategy and model were validated using a cooling water supply system as a case study. The results showed that integrating PM improved the MSP of the load-adjustable system, achieving a maximum increase of <strong>2.81 %</strong>.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"262 ","pages":"Article 111182"},"PeriodicalIF":9.4,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143899666","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}
Leila Kamalian , Huanhuan Li , Mark Ching-Pong Poo , Ana Bras , Adolf K.Y. Ng , Zaili Yang
{"title":"Analysis of the impact of climate-driven extreme weather events (EWEs) on the UK train delays: A data-driven BN approach","authors":"Leila Kamalian , Huanhuan Li , Mark Ching-Pong Poo , Ana Bras , Adolf K.Y. Ng , Zaili Yang","doi":"10.1016/j.ress.2025.111189","DOIUrl":"10.1016/j.ress.2025.111189","url":null,"abstract":"<div><div>Climate change exacerbates the occurrence of frequent Extreme Weather Events (EWEs), directly disrupting railway operations in numerous countries, notably the United Kingdom. Projections for the UK climate indicate an increase in rainfall intensity, warmer and wetter winters, hotter and drier summers, and more frequent and intense EWEs. Such climatic shifts cause increased weather-related railway delays, which in turn result in significant economic loss. This study develops a new risk model using a data-driven Bayesian Network (BN) to analyse the impact of climate-induced EWEs on UK train delays. The model quantifies the influence of various factors on delays, providing deeper insights into their individual and combined effects. The new model and the findings contribute to the disclosure of 1) the interconnections among the different variables influencing train delays, including the origin and destination of the train and traction type, and 2) the prediction of the quantitative extent to which the variables can jointly lead to train delays of different severity levels, incident reason, the month of occurrence, the responsible operator, and the train schedule type. Critical findings highlight the substantial negative impact of severe flooding on the operational reliability of the UK railway system. An important insight was the significant clustering of delays ranging from 80 to 90 min, particularly on Fridays, suggesting the need for targeted operational interventions in specific regions. Additionally, the analysis identified December as the most hazardous month for train delays due to EWEs, with January and July also showing elevated risk levels. This paper offers valuable insights for transport planners, enabling them to prioritise climate-related scenarios causing the most severe train delays and to formulate the associated adaptation measures and strategies rationally.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"262 ","pages":"Article 111189"},"PeriodicalIF":9.4,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143890545","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":"The health prediction of assembly robot based on feature fusion and weighted mahalanobis distance","authors":"GAO Guibing, Mingyu Cao, WANG Jun","doi":"10.1016/j.ress.2025.111173","DOIUrl":"10.1016/j.ress.2025.111173","url":null,"abstract":"<div><div>Predicting the health status of assembly robots serves as an effective means to enhance the reliability of manufacturing systems. To precisely predict the health status of robots and thereby improve the safety and reliability of manufacturing systems, a health status prediction method for assembly robots based on feature fusion and weighted Mahalanobis distance(<em>WMD</em>) is proposed.Addressing the issues of slow processing speed and suboptimal feature fusion in robot high-dimensional monitoring data processing with SAE, a method of optimizing the hyperparameters and selecting the appropriate loss function of SAE is employed to achieve the deep fusion of features of robot monitoring data, and the manifold learning method is incorporated to select the health status-sensitive features.To address the limitations of existing robot health state prediction models, particularly the risk of false \"healthy\" predictions caused by the complexity of numerous monitored parameters, the Cox-Box transformation is applied to the WMD of sensitive features. A robot health state monitoring model is then designed based on the transformed WMD, enabling more accurate and reliable monitoring of robot health status. An assembly robot on a production line is used as an example to demonstrate the effectiveness of the proposed method in monitoring robot health status.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"262 ","pages":"Article 111173"},"PeriodicalIF":9.4,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143887350","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":"Enhancing risk perception by integrating ship interactions in multi-ship encounters: A Graph-based Learning method","authors":"Kaisen Yang, Dong Yang, Yuxu Lu","doi":"10.1016/j.ress.2025.111150","DOIUrl":"10.1016/j.ress.2025.111150","url":null,"abstract":"<div><div>The navigation safety of autonomous surface ships depends on risk perception and avoidance in advance, which is based on accurate trajectory prediction of other ships. Sequential neural networks in deep learning have demonstrated reliable predictions in navigation scenarios with limited multi-ship interactions. However, accurately predicting trajectory changes caused by ship interactions remains challenging, as these predictions are based on mutually independent historical trajectories. In multi-ship encounters, trajectory predictions that lack interaction considerations can cause subsequent risk perception away from the actual future risk, thereby compromising navigation safety. In this study, we propose a method, the Graph-based Learning model for Risk Perception (GLRP), for risk perception based on interactive trajectory prediction. It introduces a variational graph auto-encoder to simulate the uncertain actions of ships in interactive environments, and takes the self-attention block to learn global time dependencies. GLRP establishes a learning channel from ship interactions to ship trajectories, allowing predictions based on exchanged trajectory inputs. The experiments indicate that GLRP reduces the distance to the closest point of approach error by 5. 45% and the time to the closest point of approach error by 4. 85% compared to individual sequence models. It improves navigation safety by enhancing the reliability of risk perception. The implementation code of this work is available at: <span><span>https://github.com/KaysenWB/RESS_GLRP</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"261 ","pages":"Article 111150"},"PeriodicalIF":9.4,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143879313","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":"Selective maintenance optimization for mission-oriented dynamic dependent systems under uncertain future operating environments","authors":"Xiaoning Feng, Xiaohui Chen, Lin Zhang","doi":"10.1016/j.ress.2025.111124","DOIUrl":"10.1016/j.ress.2025.111124","url":null,"abstract":"<div><div>Various selective maintenance (SM) models have been proposed to address the maintenance optimization problem for mission-oriented dependent systems (MODS). However, the effectiveness of these models depends on two assumptions: (1) the system operates in a deterministic environment, and (2) the dependencies are unchanged over the life cycle. Considering that future operating environments are generally stochastic and that the stochastic-dependencies (s-dependencies) between components/subsystems could be dynamically affected by maintenance activities and operating environments, traditional models may not meet the demand for accurate reliability assessment in real engineering. Therefore, this paper proposes a novel SM and repairpersons assignment (SM-RA) model for mission-oriented dynamic dependent systems (MODDS). In the proposed model, probabilistically occurring operating environments alter system reliability by directly impacting the failure models of sensitive components and indirectly influencing those of non-sensitive components. Subsequently, multilevel s-dependencies between components/subsystems in the MODDS are modeled by employing hierarchical Archimedean copulas (HACs). The scenario-based dependency parameters for each level in the copula function after maintenance are dynamically updated using multi-stage maximum likelihood estimation (MLE). Finally, a differential evolution (DE) algorithm is designed to solve the optimization model, and the effectiveness of the proposed method is verified by numerical examples.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"262 ","pages":"Article 111124"},"PeriodicalIF":9.4,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143879038","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}
Yixin Jiang , Jun Zhou , Xing Wu , Tao Liu , Xiaoqin Liu
{"title":"Vision-based bearing fault diagnosis under non-stationary conditions using optimized short-time concentrated transform method","authors":"Yixin Jiang , Jun Zhou , Xing Wu , Tao Liu , Xiaoqin Liu","doi":"10.1016/j.ress.2025.111183","DOIUrl":"10.1016/j.ress.2025.111183","url":null,"abstract":"<div><div>The condition of rolling bearings is closely related to the economy and safety of industrial production. The fault diagnosis of bearing under time-varying speed can realize the state analysis more comprehensively and deeply. However, due to the influence of a complex industrial field environment, there are many problems in equipment signal acquisition, and it’s difficult to achieve efficient real-time monitoring and acquisition. Limited by the difficulty of image matching and the extremely weak amplitude, there are still few research results on visual fault diagnosis of bearings. Therefore, in this paper, visual vibration measurement is introduced into the field of bearing fault diagnosis. Combined with LK optical flow method, the vibration signal is collected and extracted by an industrial high-speed camera. An enhanced time-frequency (TF) resolution method based on improved short-time centralized transform is proposed to effectively improve TF resolution and extract ridge line, to realize bearing fault diagnosis under unsteady conditions through video signal. A numerical simulation signal and rotating machinery fault simulation experiment system are used to verify the method. The results show that the vision-based signal acquisition method is feasible, and the proposed method is effective for TF analysis of bearing faults under unstable conditions based on video signals.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"262 ","pages":"Article 111183"},"PeriodicalIF":9.4,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143879040","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":"Dynamic risk-informed verification prioritization for Complex Product Systems: A tri-metric approach using a Multi-State Hierarchical Bayesian Network","authors":"Chenchen Dong, Yu Yang","doi":"10.1016/j.ress.2025.111146","DOIUrl":"10.1016/j.ress.2025.111146","url":null,"abstract":"<div><div>Complex Product Systems (CoPS) present unique challenges for Design Verification and Validation (V&V) due to tightly coupled, multi-disciplinary parameters and dynamic failure propagation. To address these challenges, this paper proposes a Multi-State Hierarchical Bayesian Network (MHBN) framework, coupled with a tri-metric approach — integrating the Degree of System Risk Reduction, Degree of System Performance Enhancement, and an Attribution Entropy measure. By reframing conventional failure mode analysis into hierarchical decomposition, fuzzy-driven probability modeling, and the formulation of a novel verification priority criterion, the method holistically captures interdependencies and uncertainties often overlooked by static approaches. In a case study on an automatic chemiluminescence immunoassay analyzer, empirical results and expert feedback revealed three key outcomes. First, the MHBN-based method distinguished mid-level components with clearer causal relationships as more cost-effective verification targets compared to top-level subsystems. Second, implementing the tri-metric guidance reduced total test hours by approximately 27% through strategic resource reallocation from high-entropy nodes to pivotal ones. Third, improved differentiation of critical priorities enabled early detection of design flaws — especially in the Pipette Mechanism — thus avoiding expensive rework. Overall, these findings underscore the value of integrating Bayesian inference with entropy concepts to support informed V&V decision-making in CoPS, offering a robust and adaptive alternative to conventional failure mode analysis.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"262 ","pages":"Article 111146"},"PeriodicalIF":9.4,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143887352","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}