Reliability Engineering & System Safety最新文献

{"title":"A new fault detection method based on an updatable hybrid model for hard-to-detect faults in nonstationary processes","authors":"Jie Dong ,&nbsp;Daye Li ,&nbsp;Zhiyu Cong ,&nbsp;Kaixiang Peng","doi":"10.1016/j.ress.2025.110920","DOIUrl":"10.1016/j.ress.2025.110920","url":null,"abstract":"<div><div>Fault detection is an effective means to guarantee the stable operation of industrial production. Fault signals are easily masked by nonstationary trends in the variables, which leads to hard-to-detect faults in nonstationary processes. In this paper, an updatable hybrid model for fault detection is proposed for the nonstationary characteristics and hard-to-detect faults of industrial processes. First, the stationary residuals of the nonstationary variables are combined with the stationary variables to form a combined matrix. Second, a monitoring model based on slow-feature-analysis-local-outlier-factor (SFA-LOF) is constructed, which extracts the slow features in the combined matrix and introduces a local outlier factor as the monitoring index. Third, the sensitive variables of faults that are hard to detect using SFA-LOF are screened, and refined models based on Kullback–Leibler divergence are constructed for hard-to-detect faults. Then, an updatable hybrid model based on the SFA-LOF model and the refined model is proposed. The hybrid model matches the detection models to the faults and is able to update the hybrid model by developing refined models. Finally, the Tennessee Eastman process is used to validate the effectiveness of the proposed fault detection framework.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"259 ","pages":"Article 110920"},"PeriodicalIF":9.4,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143474337","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 new multi-layer performance analysis of unmanned system-of-systems within IoT","authors":"Kaixuan Wang ,&nbsp;Tingdi Zhao ,&nbsp;Yuan Yuan ,&nbsp;Zhenkai Hao ,&nbsp;Zhiwei Chen ,&nbsp;Hongyan Dui","doi":"10.1016/j.ress.2025.110953","DOIUrl":"10.1016/j.ress.2025.110953","url":null,"abstract":"<div><div>Internet of Things (IoT)-enabled unmanned system-of-systems (USoS) is vital in disaster management, rescue operations, and military missions. However, research on performance loss and improvement strategies of USoS under multiple shocks has been limited. Thus, evaluating performance loss and developing improvement strategies for USoS is critical to boosting mission capability and efficiency. This paper presents a multi-layer performance analysis method for USoS within the IoT framework. Firstly, we established a multi-layer USoS structure, dividing it into physical, communication, and command layers to address variable performance and mission baselines. Secondly, an USoS performance loss model is established based on the degradation-threshold-shock models and the signal-to-noise-and-interference ratio to enhance USoS performance evaluation accuracy. Thirdly, performance improvement strategies of USoS are proposed by combining the observe, orient, decide, and act (OODA) loop with the minimum cost maximum flow theory to optimize resource allocation and reconfigure emergency links. Finally, a sea-air collaborative USoS serves as a case study to validate the efficacy of the proposed method, showing significant post-implementation performance gains, and offering a reference for mitigating performance loss and enhancing reliability during multiple shocks.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"259 ","pages":"Article 110953"},"PeriodicalIF":9.4,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479973","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":"Enhanced prediction of pipe failure through transient simulation-aided logistic regression","authors":"Dan Zhong,&nbsp;Chaoyuan Huang,&nbsp;Wencheng Ma,&nbsp;Liming Deng,&nbsp;Jinbo Zhou,&nbsp;Ying Xia","doi":"10.1016/j.ress.2025.110913","DOIUrl":"10.1016/j.ress.2025.110913","url":null,"abstract":"<div><div>To reduce leakage and improve the stability of the water supply system, water companies are increasingly adopting pipe failure prediction models based on hydraulic and non-hydraulic factors. However, these companies often face the challenge of limited data and conventional hydraulic factors have limited predictive capability in capturing the complex dynamics of pipe failures. This study proposed a logistic regression model based on hydraulic transient simulation, illustrated with the real case of a Chinese city. The data recorded included 246 pipe failures in one year. The model considered the influence of pressure, flow rate variations, and the network topology of the water supply system through hydraulic transient simulation and quantitatively analyzed the simulation results. The logistic regression model combined non-hydraulic factors with the quantitative analysis results of hydraulic factors to predict pipe failures. This study risk-categorized six areas that were prone to pipe failures. The developed model demonstrated significant accuracy and reliability in predicting pipe failures at high-risk levels. 75.61 % of true failure events were correctly predicted and the area under the curve values (AUC) value increased from 0.706 to 0.809 when incorporating transient simulation. This demonstrates that the model is effective in capturing the dynamic characteristics of the hydraulic factors and exhibits a high degree of accuracy even with a limited amount of data. This provides a feasible solution for water companies to accurately predict pipe failures.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"260 ","pages":"Article 110913"},"PeriodicalIF":9.4,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143547939","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":"SelectSeg: Uncertainty-based selective training and prediction for accurate crack segmentation under limited data and noisy annotations","authors":"Chen Zhang ,&nbsp;Mahdi Bahrami ,&nbsp;Dhanada K. Mishra ,&nbsp;Matthew M.F. Yuen ,&nbsp;Yantao Yu ,&nbsp;Jize Zhang","doi":"10.1016/j.ress.2025.110909","DOIUrl":"10.1016/j.ress.2025.110909","url":null,"abstract":"<div><div>The performance of deep learning models in crack segmentation heavily depends on the availability of large-scale, pixel-wise annotated datasets. However, such annotation is costly to acquire, and can be noisy due to the complexity of crack patterns and the subjectivity of human annotators. To obtain accurate crack segmentation models under noisy annotations, we propose SelectSeg – a four-stage uncertainty-based framework. First, we start with training a deep ensemble of segmentation models to capture the crack prediction uncertainties. Secondly, an uncertainty-based filtering mechanism identifies possibly noisy annotations. Thirdly, semi-supervised learning leverages the information from both reliably annotated data (labeled) and unreliably annotated data (unlabeled) to retrain the segmentation model. Finally, a selective prediction mechanism allows the model to abstain from making predictions on challenging cases, enhancing the overall workflow reliability. Experimental results on real-world crack datasets demonstrate that SelectSeg outperforms existing methods in noisy annotation scenarios. Both selective training and prediction bring significant accuracy improvement.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"259 ","pages":"Article 110909"},"PeriodicalIF":9.4,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143488961","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":"Hierarchical structure analysis of water distribution networks coupling pipeline dual graph and infomap algorithm","authors":"Wen Zeng ,&nbsp;Jingya Hu ,&nbsp;Boyang Cui ,&nbsp;Zhijang Yang ,&nbsp;Zhen Hu ,&nbsp;Cuiyan Han ,&nbsp;Li Bai","doi":"10.1016/j.ress.2025.110945","DOIUrl":"10.1016/j.ress.2025.110945","url":null,"abstract":"<div><div>Water distribution networks (WDNs) are essential urban infrastructure networks that play a crucial role in maintaining the stability and well-being of a city's residents. Meanwhile, effective structural feature extraction and partitioning plays a vital role in optimizing water supply operations. However, WDNs possess a complex network structure constrained by geography and a large scale. Understanding the hierarchical structure of WDNs through network science algorithms remains challenging. Additionally, simplifying the expression of the network structure is an urgent concern. In this paper, to solve the previously raised issues, we propose a hierarchical community mining method that applies Infomap algorithm partitioning in a hierarchical procedure. This method combines the Pipeline Dual Graph (PDG) model with the Infomap algorithm. The PDG model is constructed and then, the Infomap algorithm is used to construct randomized travel paths and group coding rules to solve the minimum coding length and find the optimal network multi-level partition. Experimental results demonstrate that the PDG model effectively simplifies the representation of the network structure and has obvious scale-free characteristics. In addition, the results show that the node distribution is more even. More importantly, this method can effectively reduce the number of partitions while maintaining the modular performance of networks.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"260 ","pages":"Article 110945"},"PeriodicalIF":9.4,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143547944","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 reliability method for assessing dam slope stability by incorporating intrinsic correlations of rockfill materials","authors":"Haoran Yang,&nbsp;Chen Chen,&nbsp;Wenjian Zhao,&nbsp;Xiang Lu,&nbsp;Pengtao Zhang,&nbsp;Jianghan Xue","doi":"10.1016/j.ress.2025.110961","DOIUrl":"10.1016/j.ress.2025.110961","url":null,"abstract":"<div><div>Recently, slope reliability analysis based on probabilistic theory has advanced, most of which treat material properties solely as independent variables. However, the physical and mechanical parameters of rockfill are highly interrelated, ignoring these correlations can yield in inaccurate assessments of slope stability. Therefore, a novel method incorporating intrinsic correlation between material parameters for slope reliability analysis is proposed. Initially, the statistical characteristics of 36 rockfill dams in China are analyzed to determine the best marginal distribution for each Duncan-Chang E-B model parameter using the Akaike Information Criterion. The Kendall rank correlation coefficient is then used to reveal the relationships between the parameters, based on which a multidimensional joint probability model can be established by vine copula. Finally, the surrogate model of the performance function is developed, facilitating the slope reliability analysis that incorporates intrinsic correlations. The method is applied to the DL high rockfill dam, and results indicate that neglecting intrinsic correlations increases the slope failure probability and reduces the dam slope stability, resulting in overly conservative designs. In contrast, considering interrelationships provides a more accurate representation of practical scenarios and avoids the parameter distortion.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"259 ","pages":"Article 110961"},"PeriodicalIF":9.4,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143510494","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":"Dual sampling method for evaluating uncertainty when updating a Bayesian estimation model of a high-speed railway bridge","authors":"Haruki Yotsui ,&nbsp;Kodai Matsuoka ,&nbsp;Kiyoyuki Kaito","doi":"10.1016/j.ress.2025.110901","DOIUrl":"10.1016/j.ress.2025.110901","url":null,"abstract":"<div><div>In Bayesian model updating, the parameters and uncertainties of a numerical model are updated with measured values to reproduce the conditions of an existing structure. However, the correlation of updated model parameters makes distortion of the tail space of the joint posterior distribution and uncertainty assessment difficult. To overcome this, a new uncertainty estimation methodology, dual Markov chain Monte Carlo (MCMC) method, is proposed in this study. First, the approximate shape of the joint posterior distribution is estimated and an empirical distribution of the likelihood is obtained by using the MCMC method. Second, the likelihood is transformed by using the obtained empirical distribution, and the tail space is estimated by using the replica exchange Monte Carlo method (REMC). The effectiveness of the proposed methodology is verified in updating a Bayesian structural model of a high-speed railway bridge using bridge acceleration during train passages. The joint posterior distribution of the estimated bridge frequency, modal damping ratio, and support stiffness had a large tail space distortion due to the correlation between each parameter. In general MCMC method, the number of MCMC samples corresponding to tail space is small, making it difficult to estimate the uncertainty. In addition, the model using the lower 5% confidence interval of the posterior distribution, which assumes each parameter to be independent, deviates significantly from the measurement results. On the other hand, the parameter sets expressing the tail space of posterior distribution obtained by proposed dual MCMC are efficiently estimated because the first step information is reflected in the second step sampling process. In addition, experimental results showed that the model updated by the proposed methodology could accurately estimate the resonance speed and evaluate the safety of the measured values while the model updated only by the MCMC method could not accurately estimate.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"259 ","pages":"Article 110901"},"PeriodicalIF":9.4,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing human situation awareness reliability considering fatigue and mood using EEG data: A Bayesian neural network-Bayesian network approach","authors":"Song Ding ,&nbsp;Lunhu Hu ,&nbsp;Xing Pan ,&nbsp;Dujun Zuo ,&nbsp;Liuwang Sun","doi":"10.1016/j.ress.2025.110962","DOIUrl":"10.1016/j.ress.2025.110962","url":null,"abstract":"<div><div>Situation awareness (SA) assessment is the process of acquiring and maintaining SA, which serves as a crucial indicator of operator task performance and behavioral safety in human-machine interaction. SA reliability is the evaluation of how well SA is established, and it is also the goal of SA assessment. Nonetheless, current SA assessment models rarely consider the influence of human physiological states, such as fatigue and mood, and rely heavily on subjective data. To address these deficiencies, this paper proposes a SA assessment model based on a Bayesian Neural Network (BNN) and Bayesian Network (BN), with a focus on examining the impact of fatigue and mood on the SA reliability. Firstly, fatigue and mood state classification models are developed using EEG data based on a BNN, and the uncertainty is assessed. Secondly, a BN model for SA reliability evaluation is proposed, where the uncertainty of BNN outputs is used as the prior probability, and conditional probability tables are established based on experimental statistics. Finally, a SA experiment is conducted using a civil aviation scenario based on the SAGAT platform to validate the proposed model. This model overcomes the limitations of previous approaches by leveraging objective physiological data and experimental statistics to infer the influence of physiological states on the SA reliability.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"260 ","pages":"Article 110962"},"PeriodicalIF":9.4,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143529769","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":"Degradation variation pattern mining based on BEAST time series decomposition integrated functional principal component analysis","authors":"Yu Zhou ,&nbsp;Shenyan Liu ,&nbsp;Gang Kou ,&nbsp;Fengming Kang","doi":"10.1016/j.ress.2025.110952","DOIUrl":"10.1016/j.ress.2025.110952","url":null,"abstract":"<div><div>The variety of operational conditions among comparable systems in a fleet leads to the creation of numerous samples (having multiple degradation paths) and information regarding system performance (featuring multiple state variables) within the fleet. A common technique for modeling degradation variation patterns in such fleets is functional principal component analysis, albeit often resulting in a loss of information on mutations related to the degradation of the system. This paper proposes a method to mine degradation variation patterns through a Bayesian estimator of abrupt change, seasonal change, and trend time-series decomposition integrated functional clustering. Assume that the functional characteristics evolve over time in the degradation paths of repairable systems, prompting the utilization of functional data analysis methods for clustering the corresponding degradation variation patterns. The BEAST method is used to analyze the impact of individual degradation variations on repairable systems, which can differentiate between abrupt changes, seasonal variations, and trends in the population of repairable systems. We then use this analysis to develop preventive maintenance optimization models and analyse the impact of change-points in the degradation process on the maintenance strategy. The study offers a robust methodology for analyzing fleet degradation, thereby enhancing the understanding of degradation patterns and optimizing preventive maintenance strategies.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"259 ","pages":"Article 110952"},"PeriodicalIF":9.4,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143510497","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 sequential diagnostic strategy generation transformation method for large-scale systems based on multi-signal flow graph model and multi-objective optimization","authors":"Jingyuan Wang ,&nbsp;Zhen Liu ,&nbsp;Xutian Yao ,&nbsp;Yong Wang ,&nbsp;Qi Li ,&nbsp;Jinhua Mi","doi":"10.1016/j.ress.2025.110922","DOIUrl":"10.1016/j.ress.2025.110922","url":null,"abstract":"<div><div>The multi-signal flow graph model is widely used in sequential fault diagnosis of complex systems due to its low modeling difficulty and fast diagnostic speed. Based on this model, testers can obtain a strategy to guide the diagnosis by solving the optimal sequential strategy generation problem (OSP). As system complexity increases, diagnostic requirements for various costs are increasingly highlighted, and the optimization problem also evolves from small-scale single-objective OSP to large-scale multi-objective OSP (LM-OSP). However, due to the complexity of the objective space and the Markov property of decision variables, LM-OSP is challenging to solve with conventional algorithms. To address this, this paper transforms the original LM-OSP into a more tractable designated region mapping problem (DRMP) and solves it with swarm intelligence search algorithms (SISAs) for better solutions. First, distributions are approximated to make the objective space continuous. Second, the decision space is linearized by converting the spatial data structure. Based on the continuity and linearization, the transformed DRMP is established, and basic steps for applying any SISA are determined. Finally, strategies with a comprehensive 8∼10-fold diagnostic performance improvement can be achieved in simulation and real case experiments.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"259 ","pages":"Article 110922"},"PeriodicalIF":9.4,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143510498","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}