Reliability Engineering & System Safety最新文献_第7页

A systematic procedure for the analysis of maintenance reports based on a taxonomy and BERT attention mechanism

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-01-15 DOI: 10.1016/j.ress.2025.110834

Dario Valcamonico , Piero Baraldi , July Bias Macêdo , Márcio Das Chagas Moura , Jonathan Brown , Stéphane Gauthier , Enrico Zio

{"title":"A systematic procedure for the analysis of maintenance reports based on a taxonomy and BERT attention mechanism","authors":"Dario Valcamonico , Piero Baraldi , July Bias Macêdo , Márcio Das Chagas Moura , Jonathan Brown , Stéphane Gauthier , Enrico Zio","doi":"10.1016/j.ress.2025.110834","DOIUrl":"10.1016/j.ress.2025.110834","url":null,"abstract":"<div><div>This work proposes a systematic procedure for analyzing maintenance reports to support maintenance decision-making for a fleet of similar systems. The proposed procedure allows achieving three objectives: (1) grouping maintenance interventions, (2) identifying common characteristics in the maintenance interventions, and (3) recognizing occurrences of rare events of maintenance intervention. Specifically, the attention mechanism of Bidirectional Encoder Representation from Transformer (BERT) and the Density Based Spatial Clustering Applications with Noise (DBSCAN) methods are combined to group maintenance interventions according to their similarity of stated features. A taxonomy of the words used in the textual reports to state the maintenance interventions is developed to systematically identify common features of the clusters, such as the involved components, their working state, the occurred failures or malfunctions, the performed maintenance actions and the personnel that has performed the intervention. The proposed procedure is applied to a repository of reports of maintenance interventions performed on mechanical and electric components of traction systems of a fleet of trains. The obtained results show that it can effectively support decision-making on the maintenance of traction systems.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"257 ","pages":"Article 110834"},"PeriodicalIF":9.4,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143219608","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}

引用次数: 0

Enhancing reliability calculation for one-output k-out-of-n binary-state networks using a new BAT

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-01-15 DOI: 10.1016/j.ress.2025.110835

Wei-Chang Yeh

{"title":"Enhancing reliability calculation for one-output k-out-of-n binary-state networks using a new BAT","authors":"Wei-Chang Yeh","doi":"10.1016/j.ress.2025.110835","DOIUrl":"10.1016/j.ress.2025.110835","url":null,"abstract":"<div><div>Evaluation of network reliability is a crucial aspect of system planning, design, and management. A k-out-of-n network is an important extension of the k-out-of-n system, which is a repairable redundancy binary-state system with <em>n</em> parallel components. The system fails if and only if at least k consecutive components fail, where k is an integer between 1 and <em>n</em>. In the proposed problem, at least k units of input flow are required to activate a node to output one unit of flow. This one-output <em>k-</em>out<em>-</em>of<em>-n</em> binary-state network model, along with a novel algorithm proposed to calculate its reliability, is motivated by real-life applications. The binary-addition-tree algorithm (BAT) can address this problem. By modifying the BAT and incorporating the novel cut-based layered-search method (CLSA), a novel algorithm is proposed to calculate the reliability of the proposed k-out-of-n binary-state network. The proposed algorithm is not limited to its original scope. The proposed algorithm has been extended to address additional scenarios. Specifically, it is now capable of solving traditional multi-output <em>k-</em>out<em>-</em>of<em>-n</em> networks. Based on both theoretical and empirical analyses conducted on examples, the proposed algorithm demonstrates greater efficiency and flexibility compared to the traditional BAT.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"257 ","pages":"Article 110835"},"PeriodicalIF":9.4,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143286640","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

Mathematical modeling of solar farm performance degradation in a dynamic environment for condition-based maintenance

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-01-15 DOI: 10.1016/j.ress.2024.110778

Yaxin Shen , Mitra Fouladirad , Antoine Grall

{"title":"Mathematical modeling of solar farm performance degradation in a dynamic environment for condition-based maintenance","authors":"Yaxin Shen , Mitra Fouladirad , Antoine Grall","doi":"10.1016/j.ress.2024.110778","DOIUrl":"10.1016/j.ress.2024.110778","url":null,"abstract":"<div><div>This paper aims to address the challenge of modeling and optimizing condition-based maintenance policies for a degraded solar farm in varying environmental conditions. Dust accumulation and temperature increases are the two main causes of performance reduction and energy loss in the system. In this research, dust accumulation is modeled by the non-homogeneous compound Poisson process, and three different mathematical models for the efficiency reduction of photovoltaic panels due to dust accumulation are considered. The effects of wind and rain, taken as covariates, on dust accumulation and temperature are investigated by stochastic process modeling. The covariate process is considered a time-homogeneous Markov chain with finite state space. The PV surface temperature is modeled by a non-homogeneous Markov chain with finite state space and transition matrices under covariate states. Different PV panels exhibit varied degradation rates, influenced by their position and tilt angle to sunlight. In the framework of the system, we derive multiple maintenance policies aimed at achieving the minimum cost criterion. The expected long-term average maintenance costs under different covariate conditions and maintenance policies are evaluated through simulation experiments to compare the effectiveness of each policy.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"257 ","pages":"Article 110778"},"PeriodicalIF":9.4,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143218981","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

Monitoring of operational resilience on urban road network: A Shaoxing case study

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-01-15 DOI: 10.1016/j.ress.2025.110836

Jianwei Du , Gang Ren , Jialei Cui , Qi Cao , Jian Wang , Chenyang Wu , Jiefei Zhang

{"title":"Monitoring of operational resilience on urban road network: A Shaoxing case study","authors":"Jianwei Du , Gang Ren , Jialei Cui , Qi Cao , Jian Wang , Chenyang Wu , Jiefei Zhang","doi":"10.1016/j.ress.2025.110836","DOIUrl":"10.1016/j.ress.2025.110836","url":null,"abstract":"<div><div>Urban road networks (URNs), which are the critical infrastructure of a city, are fragile when faced with external disruptions. Efficient and accurate analyses of URN resilience of URNs could provide a new perspective for enhancing their ability to withstand, adapt, and recover from disruptive events. This study focused on the resilience evaluation and prediction of URN. A time-varying belief Markov-based resilience model was proposed to analyze the Operational Resilience (OR), which integrates link usability and driving efficiency. The OR is then converted to a normalized scale (COR), which is easier for decision-makers to understand. Finally, a case study was conducted to validate the proposed model. The results showed that demand, link capacity, disaster intensity, and road network structure are significant factors affecting the OR of a URN. Within the OR threshold, the recovery time is generally half the response time and is more stable among different links and precipitation intensities. It has been proven to have satisfactory performance in the estimation and prediction of resilience, which can capture the long-term OR of URN and identify key links and regions that require more attention. This approach could assist decision-makers in developing effective measures for disruptive events.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"257 ","pages":"Article 110836"},"PeriodicalIF":9.4,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143219617","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

Benchmark transformation neural network for health indicator construction under time-varying speed and its application in machinery prognostics

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-01-15 DOI: 10.1016/j.ress.2025.110823

Jiahong Yang , Jianghong Zhou , Yi Chai , Dingliang Chen , Yi Qin

{"title":"Benchmark transformation neural network for health indicator construction under time-varying speed and its application in machinery prognostics","authors":"Jiahong Yang , Jianghong Zhou , Yi Chai , Dingliang Chen , Yi Qin","doi":"10.1016/j.ress.2025.110823","DOIUrl":"10.1016/j.ress.2025.110823","url":null,"abstract":"<div><div>A health indicator (HI) is usually applied to predict the remaining useful life (RUL) of machinery. The current HI construction methods typically only focus on constant operating conditions (such as speed or load), rendering them ineffective for variable-speed conditions. To address this gap, this paper proposes a HI construction method for machines under time-varying speed conditions based on benchmark transformation neural networks (BTNN). First, the baseline speed range is determined, and the baseline state observations are identified. Then, with the identified baseline observations, a performance degradation model is established via the double exponential function. Next, BTNN is innovatively proposed using the fitted degradation model, the monitoring state, and speed data to adaptively perform the complex nonlinear mapping from non-baseline observations to baseline values, avoiding the problem of selecting different baseline transformation functions. Compared with the HI constructed by a transformation function and the dimensionless HI, the proposed method unifies state observations at various speeds onto the baseline speed through BTNN, enhancing the comprehensive performance of HI. Comparative experiments on the RUL prediction of turbofan engines and wind turbine bearings reveal that the HI extracted by BTNN exhibits stronger prognosis capabilities than other classical and advanced HIs.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"257 ","pages":"Article 110823"},"PeriodicalIF":9.4,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143286448","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

Attack strategies and reliability analysis of Wireless Mesh Networks considering cascading failures

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-01-15 DOI: 10.1016/j.ress.2025.110832

Hongyan Dui , Jiabao Zhai , Xiuwen Fu

{"title":"Attack strategies and reliability analysis of Wireless Mesh Networks considering cascading failures","authors":"Hongyan Dui , Jiabao Zhai , Xiuwen Fu","doi":"10.1016/j.ress.2025.110832","DOIUrl":"10.1016/j.ress.2025.110832","url":null,"abstract":"<div><div>Wireless Mesh Networks (WMNs) are vital to modern infrastructure, and attacks on WMNs can lead to paralysis of interdependent systems, causing significant social and economic consequences. However, existing studies often assume all attacks coincide, focusing on cascading failures from a single perspective while neglecting specific attack strategies. This study is the first to apply sequential attack strategies to WMNs and conduct a comparative analysis with synchronous strategies. First, we propose a system model for WMNs that incorporates path loss and link capacity, representing real-world scenarios. Secondly, we introduce two novel reliability metrics, transmission reliability and reliability degradation rate, to quantify the impact of attacks. In the final case study, we analyze the effects of synchronous and sequential attack strategies under four node attack rules. Results reveal that sequential attack strategies dynamically identify and exploit critical nodes, causing prolonged degradation of transmission reliability and amplifying cascading failures. Compared to synchronous attack strategies, sequential attack strategies increase the global reliability degradation rate and reliability degradation rate during the attack phase by 28.62 % and 55.36 %, respectively. Therefore, sequential attack strategies should combine these two node attack rules to achieve maximum impact. These findings confirm that the proposed sequential attack strategy effectively disrupts network performance and provides meaningful insights for developing WMN defense strategies.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"257 ","pages":"Article 110832"},"PeriodicalIF":9.4,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143286635","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

Condition-based maintenance for redundant systems considering spare inventory with stochastic lead time

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-01-15 DOI: 10.1016/j.ress.2025.110837

Jun Wang , Yuqiang Fu , Jian Zhou , Lechang Yang , Yating Yang

{"title":"Condition-based maintenance for redundant systems considering spare inventory with stochastic lead time","authors":"Jun Wang , Yuqiang Fu , Jian Zhou , Lechang Yang , Yating Yang","doi":"10.1016/j.ress.2025.110837","DOIUrl":"10.1016/j.ress.2025.110837","url":null,"abstract":"<div><div>Condition-based maintenance (CBM) and spare provisioning are both important to guarantee the operation of redundant systems composed of degrading components. However, most existing studies on joint optimization of CBM and spare inventory assume maintenance actions are instantaneous and the lead time for spares are fixed, which are not consistent with the reality. Therefore, this paper focus on the joint optimization problems to minimize the total cost rate considering stochastic maintenance time for components and stochastic lead time for spares. The problem is modeled as a Markov decision process model and solved by an improved reinforcement learning algorithm, i.e., the improved Q-learning algorithm, which converges more quickly and reaches a smaller value of the total cost rate than the traditional Q-learning algorithm. Moreover, the simulated environment based on discrete event simulation method is introduced in detail and the convergence of the algorithm is proved theoretically. Based on the numerical study, we further demonstrate the convergence and effectiveness of the proposed algorithm and perform sensitivity analysis on several model parameters to provide management insights for decision makers.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"257 ","pages":"Article 110837"},"PeriodicalIF":9.4,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143286642","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

Risk influencing factors on the consequence of waterborne transportation accidents in China (2013–2023) based on data-driven machine learning

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-01-14 DOI: 10.1016/j.ress.2025.110829

Weiliang Qiao , Enze Huang , Meng Zhang , Xiaoxue Ma , Dong Liu

{"title":"Risk influencing factors on the consequence of waterborne transportation accidents in China (2013–2023) based on data-driven machine learning","authors":"Weiliang Qiao , Enze Huang , Meng Zhang , Xiaoxue Ma , Dong Liu","doi":"10.1016/j.ress.2025.110829","DOIUrl":"10.1016/j.ress.2025.110829","url":null,"abstract":"<div><div>Early warning on the basis of RIFs data is widely considered as an effective way to prevent waterborne transportation accidents, and the performance of warning model is critical. To develop a warning model with good performance, in this study, a data-driven based comprehensive machine learning algorithm, namely BiLSTM-CNN-RF is proposed. The RIFs data used to train the proposed algorithm is extracted from the 1090 waterborne transportation accident investigation reports during 2013–2023 in China, the collected data is first pre-processed to establish the input sample set of the algorithms. Meanwhile the importance of RIFs is also quantitatively analyzed. The traditional machine learning algorithms, such as RF, SVM, MPL, and GRU, are also involved in this study to verify the performance of the proposed comprehensive algorithm. The RIFs data is then fed into these five machine learning algorithms, the prediction results of “Accident type” and “Accident grade” are used to examine their prediction performance. The results show that the performance of the proposed BiLSTM-CNN-RF algorithm is better than the four traditional machine learning algorithms, especially for prediction accuracy, and another superiority is the good applicability in case of small sample data volume.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"257 ","pages":"Article 110829"},"PeriodicalIF":9.4,"publicationDate":"2025-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143219605","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

Corrigendum to “Risk assessment of main accident causes at highway-rail grade crossings” [Reliability Engineering & System Safety Volume 256 (2025) 110764]

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-01-14 DOI: 10.1016/j.ress.2025.110826

Xiyuan Chen , Xiaoping Ma , Limin Jia , Fei Chen

引用次数: 0

A novel hybrid approach combining PDEM and bayesian optimization deep learning for stochastic vibration analysis in train-track-bridge coupled system

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-01-14 DOI: 10.1016/j.ress.2025.110827

Jianfeng Mao , Zheng Li , Zhiwu Yu , Lianjun Hu , Mansoor Khan , Jun Wu

{"title":"A novel hybrid approach combining PDEM and bayesian optimization deep learning for stochastic vibration analysis in train-track-bridge coupled system","authors":"Jianfeng Mao , Zheng Li , Zhiwu Yu , Lianjun Hu , Mansoor Khan , Jun Wu","doi":"10.1016/j.ress.2025.110827","DOIUrl":"10.1016/j.ress.2025.110827","url":null,"abstract":"<div><div>Train-track-bridge (TTB) system is a highly stochastic dynamical system. Deep learning has been applied to stochastic vibration analysis of TTB systems in recent years. However, most machine learning models consider only a single numerical relationship between input data and output responses. This often results in a strong dependence on training data, leading to a lack of robustness and reliability. In this paper, a novel hybrid method combining the probability density evolution method (PDEM) with an improved Bayesian optimization (BO) deep learning model (IDLM) is proposed for the efficient stochastic vibration analysis of uncertain TTB systems. This approach facilitates information exchange between the train-bridge model and the deep learning model. In this approach, PDEM is integrated into the deep learning framework to achieve a cohesive integration of physical and numerical models. The applicability of the PDEM-IDLM method is verified by comparing the predicted stochastic responses with the results of a validated train-bridge model. Furthermore, a case study investigates the effects of training dataset size, vehicle speed, and noise level, providing additional validation of the robustness of the proposed method.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"257 ","pages":"Article 110827"},"PeriodicalIF":9.4,"publicationDate":"2025-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143219269","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