Reliability Engineering & System Safety最新文献_第9页

Uncertain Data Driven Predictive Maintenance: A Cost-oriented Implementation Method on Aircraft System 不确定数据驱动的预测性维修：一种面向成本的飞机系统实施方法

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-29 DOI: 10.1016/j.ress.2025.111278

Sizheng Duan, Jianzhong Sun, ZhiQiang Yu, ShanQing Liu

{"title":"Uncertain Data Driven Predictive Maintenance: A Cost-oriented Implementation Method on Aircraft System","authors":"Sizheng Duan, Jianzhong Sun, ZhiQiang Yu, ShanQing Liu","doi":"10.1016/j.ress.2025.111278","DOIUrl":"10.1016/j.ress.2025.111278","url":null,"abstract":"<div><div>The increasing availability of on-board sensor data from complex systems, such as modern commercial aircraft, provides opportunities for developing data-driven health monitoring and predictive maintenance (PdM) methods. This paper proposes a health monitoring approach for commercial aircraft air conditioning systems, integrating unsupervised autoencoders with LSTM models to extract a health index (HI) and calculate the probability distribution of predicted performance parameters to represent system uncertainty. Additionally, a cost assessment model for predictive maintenance is developed to optimize maintenance decision thresholds based on the extracted health index. By simulating maintenance events for the aircraft air conditioning system within a predictive maintenance framework and applying the Gauss-LSTM-AE model to real data from a commercial aircraft fleet, this study assesses different health indicators from a cost perspective. The case study demonstrates that the proposed health monitoring method effectively identifies impending system faults. Moreover, the findings highlight that the integration of health monitoring with PdM decisions is significantly influenced by the health index and its decision threshold, which directly impacts system reliability and maintenance costs. This approach offers valuable insights into optimizing system safety by balancing predictive accuracy with economic constraints, providing a direction for improving reliability and efficiency in real-world maintenance operations.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"264 ","pages":"Article 111278"},"PeriodicalIF":9.4,"publicationDate":"2025-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144220930","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

Relaxed subset simulation for reliability estimation 可靠性估计的松弛子集仿真

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-29 DOI: 10.1016/j.ress.2025.111302

Binbin Li , Weili Xia , Zihan Liao

{"title":"Relaxed subset simulation for reliability estimation","authors":"Binbin Li , Weili Xia , Zihan Liao","doi":"10.1016/j.ress.2025.111302","DOIUrl":"10.1016/j.ress.2025.111302","url":null,"abstract":"<div><div>The practical implementation of subset simulation (SuS) may be biased in estimating the small failure probability, when the limit state function (LSF) exhibits pathological geometries that hinder the ergodicity of Markov Chain Monte Carlo (MCMC) sampling. To address this, we propose a “relaxed” version of SuS (<em>Re</em>-SuS), which replaces the conventional indicator function with a hybrid indicator function to enhance the capability of MCMC in exploring the standard normal space. This modification stems from a sequential importance sampling (SIS) interpretation of SuS, offering flexibility in selecting intermediate sampling distributions (ISDs). The hybrid indicator function incorporates both the LSF and the probability density function (PDF) of standard normal variables, acknowledging that failure events typically correspond to small PDF values. By including portions of intermediate safe domains, the ISD in <em>Re</em>-SuS slows the transition to the failure domain, improving the likelihood of identifying true design points. Various benchmark examples are presented to validate the performance of <em>Re</em>-SuS, demonstrating its robustness against misleading LSF geometries. While the estimation uncertainty is marginally higher than in the original SuS, <em>Re</em>-SuS significantly reduces the potential bias in failure probability estimation. More broadly, the SIS interpretation of SuS provides opportunities for further performance enhancements through careful design of the ISD.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"264 ","pages":"Article 111302"},"PeriodicalIF":9.4,"publicationDate":"2025-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144229939","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

Ratcheting fatigue reliability and sensitivity analysis of hydraulic pipe under in-service loadings 在役液压管道棘轮疲劳可靠性及灵敏度分析

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-29 DOI: 10.1016/j.ress.2025.111293

Zhenghong Yao , Jin Hao , Zhi Tan , Changyou Li , Jinsong Zhao

{"title":"Ratcheting fatigue reliability and sensitivity analysis of hydraulic pipe under in-service loadings","authors":"Zhenghong Yao , Jin Hao , Zhi Tan , Changyou Li , Jinsong Zhao","doi":"10.1016/j.ress.2025.111293","DOIUrl":"10.1016/j.ress.2025.111293","url":null,"abstract":"<div><div>Considering the critical role of ratcheting fatigue reliability in determining the structural integrity of hydraulic pipelines, the development of robust probabilistic fatigue theories becomes essential for optimizing design schemes. This paper focuses on the ratcheting fatigue reliability and sensitivity analysis of the hydraulic pipe subjected to sustained in-service conditions. Firstly, the deterministic finite element model analysis is adopted to determine the equivalent stress amplitude at the critical location of the pipe, thereby establishing the limit state function. An advanced experimental setup is developed to replicate the in-service loadings on the hydraulic pipe. The finite element model is systematically validated through the experimental method. Subsequently, the Kriging-based single-loop Monte Carlo simulation method is established to evaluate the ratcheting reliability of the hydraulic pipe. The effectiveness and accuracy of the developed method are validated by comparison with the traditional quasi-Monte Carlo simulation method. The influence of cyclic force amplitude and operating internal pressure on the ratcheting failure probability of the hydraulic pipe are assessed to provide guidance for reliability-based design. Finally, the ratcheting fatigue sensitivity of input random variables is evaluated to advance the theoretical framework and practical implementations of statistical analysis for the optimum design of the hydraulic pipe.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"264 ","pages":"Article 111293"},"PeriodicalIF":9.4,"publicationDate":"2025-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144195617","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

Exploring the perspective of time: A framework for dynamic assessment of leakage risk in WDNs based on a joint model of survival analysis and machine learning 探索时间的视角：基于生存分析和机器学习联合模型的wdn泄漏风险动态评估框架

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-29 DOI: 10.1016/j.ress.2025.111294

Yunkai Kang , Wenhong Wu , Yuexia Xu , Ning Liu

{"title":"Exploring the perspective of time: A framework for dynamic assessment of leakage risk in WDNs based on a joint model of survival analysis and machine learning","authors":"Yunkai Kang , Wenhong Wu , Yuexia Xu , Ning Liu","doi":"10.1016/j.ress.2025.111294","DOIUrl":"10.1016/j.ress.2025.111294","url":null,"abstract":"<div><div>Assessment of leakage risk in water distribution networks (WDNs) and implementing preventive monitoring for high-risk pipelines are widely recognized strategies for mitigating leakage-related losses. Conventional leakage risk assessment methods face three critical challenges: class imbalance, insufficient modeling of time-varying risk factors, and limited model interpretability. To address these issues, we propose an interpretable machine learning framework, Interpretable Survival Analysis with Class-Imbalance Mitigation (ISACIM). The framework synergizes static risk assessment with dynamic survival analysis to achieve spatiotemporal decoupling in leakage probabilistic evaluation. By integrating hybrid data-balancing strategies and a conditional generative adversarial network (GAN), ISACIM effectively resolves leakage sample distribution skewness. Experimental results demonstrated that ISACIM achieved a 7 % improvement in leakage pipeline prediction accuracy on real-world WDN datasets, along with enhanced survival analysis performance, 7.89 % increase in Time AUC. To overcome limitations in time-dependent risk factor analysis, we introduce Shapley Additive Explanations-based methods, systematically revealing for the first time the dynamic evolution of dominant risk factors across pipeline lifecycles: material properties and joint types dominate leakage risk during the initial service phase, while length and diameter become predominant in long-term service. Furthermore, the developed web-based WDN leakage risk assessment platform integrates predictive results with interpretability analysis, providing a decision support tool combining theoretical rigor and practicability for WDNs reliability evaluation.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"264 ","pages":"Article 111294"},"PeriodicalIF":9.4,"publicationDate":"2025-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144229935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Modelling downburst velocity fields in relation to Main Wind Force Resisting Systems 与主抗风系统有关的下爆速度场模拟

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-29 DOI: 10.1016/j.ress.2025.111300

Federico Canepa , Massimiliano Burlando , Djordje Romanic , Horia Hangan

{"title":"Modelling downburst velocity fields in relation to Main Wind Force Resisting Systems","authors":"Federico Canepa , Massimiliano Burlando , Djordje Romanic , Horia Hangan","doi":"10.1016/j.ress.2025.111300","DOIUrl":"10.1016/j.ress.2025.111300","url":null,"abstract":"<div><div>Over the past two decades, wind engineering has focused on non-synoptic wind storms, which exhibit greater spatio-temporal complexity than synoptic scale winds. Here we focus on the modelling of downburst velocity fields in relation to the way these models can be used to determine structural responses to downburst winds. Two approaches have been defined in relation to the Main Wind Force Resisting Systems (MWFRS): (i) the Gust Front Factor (GFF) from Professor Ashan Kareem’s group at Notre Dame University in USA and (ii) the Thunderstorm Response Spectrum Technique (TRST) from the late Professor Giovanni Solari’s team at the University of Genova in Italy. Both methods decompose the downburst mean wind field into a vertical profile and a time variation. Here we focus on the modelling of downburst velocity fields in terms of spatial and time characterizations including the effects of translation, atmospheric boundary layer (ABL) superposition and surface effects.</div><div>Herein, we focus on analysing how various analytical models, that include both time and space velocity variations, can be adapted to fit an experimental database of downburst-like flows (DLFs), generated at WindEEE Dome at Western University under the project THUNDERR. The calibration is conducted through the superposition of stationary mean flow fields with the effects of translation, background synoptic wind and surface roughness. Analytical models for the profile variation, the Oseguera-Bowles-Vicroy (OBV) and Wood & Kwok models, along with the sine wave models for temporal variation, are tested against this extensive database. The resulting adapted proposed models provide a potential frame on DLFs to be applied in the context of MWFRS approaches.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"264 ","pages":"Article 111300"},"PeriodicalIF":9.4,"publicationDate":"2025-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144255427","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

Modeling urban transportation safety resilience under extreme rainstorms: A catastrophe theory approach 极端暴雨条件下城市交通安全弹性建模：一种突变理论方法

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-29 DOI: 10.1016/j.ress.2025.111301

Fei Ma , Yujie Zhang , Qing Liu , Yaru Guo , Zhijie Yang , Jiaju Zhang

{"title":"Modeling urban transportation safety resilience under extreme rainstorms: A catastrophe theory approach","authors":"Fei Ma , Yujie Zhang , Qing Liu , Yaru Guo , Zhijie Yang , Jiaju Zhang","doi":"10.1016/j.ress.2025.111301","DOIUrl":"10.1016/j.ress.2025.111301","url":null,"abstract":"<div><div>Extreme rainstorm disasters severely affect urban transportation safety. To scientifically assess urban transportation safety resilience (UTSR<span><span><sup>1</sup></span></span>) and its evolutionary process under extreme rainstorm disasters, this study proposes a novel assessment method by modeling the UTSR using the catastrophe theory approach. First, a safety framework for the urban transportation system is constructed, and catastrophe theory is applied to analyze catastrophic effects on the system. Second, factors affecting UTSR are identified, and their relationships are analyzed using a stock and flow model. Finally, the effectiveness of the UTSR dynamic simulation model is analyzed using the case study of an extreme rainstorm event in Xi'an, China. The results reveal that increasing the investment levels of government regulation effort (GRE<span><span><sup>2</sup></span></span>), information synergy degree (ISD<span><span><sup>3</sup></span></span>), and municipal drainage effectiveness (MDE<span><span><sup>4</sup></span></span>) leads to modeled increases in UTSR levels by 59.44%, 50.18%, and 16.79%, respectively. The results demonstrate that strengthening GRE and ISD significantly enhances UTSR, while MDE has a relatively minor impact. This study contributes a new theoretical perspective and practical modeling tool for capturing abrupt resilience transitions, offering detailed management strategies for enhancing UTSR when facing extreme rainstorms.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"263 ","pages":"Article 111301"},"PeriodicalIF":9.4,"publicationDate":"2025-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144184861","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

Multi-state k-out-of-n: F network system performance evaluation by considering a balance dependence mechanism 考虑平衡依赖机制的多状态k- of-n: F网络系统性能评价

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-28 DOI: 10.1016/j.ress.2025.111291

Hongda Gao , Tengfei Tu , Chen Fang , Xiaoguang Zhou

{"title":"Multi-state k-out-of-n: F network system performance evaluation by considering a balance dependence mechanism","authors":"Hongda Gao , Tengfei Tu , Chen Fang , Xiaoguang Zhou","doi":"10.1016/j.ress.2025.111291","DOIUrl":"10.1016/j.ress.2025.111291","url":null,"abstract":"<div><div>In recent years, the balanced system reliability models have attracted a lot of research interests because of its strong application potential, for example in the fields of unmanned systems, energy supply systems, and production systems, etc. Network models exist widely in reality, which gives birth to the research of equilibrium system model under network structure. This study extends the binary-state <em>k</em>-out-of-<em>n</em> model to a multi-state framework, where both the components and system could exhibit varying operational conditions. In specific, firstly, the definition of the <em>k</em>-out-of-<em>n: F</em> balanced system is given by introducing a multi-state system model in which the components could be fully operational, partially operational, or failed. Secondly, we describe the system balance condition which is redefined to maintain an equal number of operational components in different working levels across in an individual sector. Thirdly, the new reliability formulas will be derived that account for the system reliability, utilizing both the order statistics and Markov chain model techniques. Finally, numerical examples highlight the practical implications and improved realism of the proposed reliability models.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"264 ","pages":"Article 111291"},"PeriodicalIF":9.4,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144229934","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

Improved genetic programming modeling of slope stability and landslide susceptibility 改进的边坡稳定性和滑坡易感性遗传规划模型

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-28 DOI: 10.1016/j.ress.2025.111296

Beichen Yu , Yingke Liu , Dongming Zhang , Bin Xu , Changbao Jiang , Chao Liu

{"title":"Improved genetic programming modeling of slope stability and landslide susceptibility","authors":"Beichen Yu , Yingke Liu , Dongming Zhang , Bin Xu , Changbao Jiang , Chao Liu","doi":"10.1016/j.ress.2025.111296","DOIUrl":"10.1016/j.ress.2025.111296","url":null,"abstract":"<div><div>The prediction of slope stability and landslide susceptibility is crucial for ensuring the safety and reliability of high slopes and disasters prevention. This study used genetic programming (GP) to predict slope stability and landslide risks. To address the limitations of GP such as local convergence and code redundancy growth and enhance prediction accuracy, hierarchical fair competition model based on K-means clustering algorithm (K-means-HFC), niche technique of similarity based on crowding (NTSC), and self-adaptive change in probability were proposed to improve the traditional GP. Then, the improved GP was used to conduct modeling research for prediction, including slope stability, land-slide dynamic characterization, probabilistic hazard of seismic landslide, and blasting vibration parameters and hazard. The results showed that K-mean-HFC and NTSC separately increased inter- and intra-cluster population diversity and promoted the fitness, further enhancing the model prediction accuracy. In the case of multi-parameter prediction, the improved GP could realize attribute reduction on the prediction parameters, eliminate the attributes unrelated to the prediction parameters, and clearly obtain the prediction formulas. By utilizing the improved GP, the prediction model of slope stability was acquired, the mutual prediction of surface displacement rate and subsurface volumetric was established, the probabilistic prediction diagram of seismic landslide in Sichuan Province was generated, the influence of prediction parameters was analyzed, and the prediction of blasting vibration parameters and hazard of slope blasting under the influence of multiple parameters was realized. The derived prediction formulas possessed a significant reference for solving the same type of slope reliability and landslide prevention problems.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"264 ","pages":"Article 111296"},"PeriodicalIF":9.4,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144195618","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

Two-stage remaining useful life prediction method across operating conditions based on small samples and novel health indicators 基于小样本和新型健康指标的两阶段剩余使用寿命预测方法

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-26 DOI: 10.1016/j.ress.2025.111290

Yiming Li, Congjie Fu, Tongshan Liu, Zhihao Hu, Guiqiu Song

{"title":"Two-stage remaining useful life prediction method across operating conditions based on small samples and novel health indicators","authors":"Yiming Li, Congjie Fu, Tongshan Liu, Zhihao Hu, Guiqiu Song","doi":"10.1016/j.ress.2025.111290","DOIUrl":"10.1016/j.ress.2025.111290","url":null,"abstract":"<div><div>A novel frequency-domain similarity-based health indicator (LR-HDSC) and a multi-scale convolutional residual gated recurrent unit (GRU) adversarial transfer model (MSCRGAT) are proposed in this paper for remaining useful life (RUL) prediction of rolling bearings under cross-operational conditions. First, a health indicator is constructed by computing the Hellinger Distance of Spectral Correlation (HDSC), applying Linear Rectification (LR) to suppress noise fluctuations. The adversarial transfer model (MSCRGAT) integrates multi-scale convolutional kernels (to capture local degradation patterns), residual GRU modules (to model temporal dependencies and mitigate gradient vanishing issues), and a dual-domain adaptation strategy (combining adversarial training and Maximum Mean Discrepancy (MMD) for domain-invariant feature alignment). This enables domain-invariant feature learning and transfer across different operating conditions. At the same time, Bayesian optimization is used for hyperparameter tuning. To verify the effectiveness, we constructed four cross-condition RUL prediction tasks using two bearing datasets, comparing MSCRGAT with mainstream methods. Experimental results demonstrate that MSCRGAT provides significantly improved prediction accuracy and robustness under varying operational conditions, notably enhancing the determination coefficient (R²). Despite occasional prediction fluctuations during rapid degradation stages, the proposed method offers an effective and reliable solution for practical equipment RUL prediction.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"264 ","pages":"Article 111290"},"PeriodicalIF":9.4,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144195619","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

A novel target-adaptive frequent pattern growth algorithm for oil well failure analysis 油井失效分析中一种新的目标自适应频繁模式增长算法

IF 9.4 1区工程技术

Reliability Engineering & System Safety Pub Date : 2025-05-26 DOI: 10.1016/j.ress.2025.111281

Xiang Wang , Xianxiang Chu , Yixin Xie , Yanfeng He , Hui Xu , Jing Guo

{"title":"A novel target-adaptive frequent pattern growth algorithm for oil well failure analysis","authors":"Xiang Wang , Xianxiang Chu , Yixin Xie , Yanfeng He , Hui Xu , Jing Guo","doi":"10.1016/j.ress.2025.111281","DOIUrl":"10.1016/j.ress.2025.111281","url":null,"abstract":"<div><div>Oil well failures can not only lead to significant economic losses but also present serious safety risks. By identifying and intervening in failure patterns, the occurrence of failures can be minimized. This paper analyzes 1522 failure records collected over three years, identifying 17 causes, including corrosion, aging, and scaling. We propose a novel target-adaptive frequent pattern growth algorithm (TAFP-Growth), comprising two core components: target frequent pattern generation and adaptive rule mining. Initially, the algorithm constructs a target-tree to identify frequent patterns. It designates the target as the rule's consequent and assigns other items as the antecedent, which helps determine the relationships among frequent patterns. By employing adaptive thresholds, the algorithm effectively addresses the difficulties of mining arising from sample imbalance. When applied to oil well failure records, this algorithm significantly speeds up the rule mining process and reduces memory consumption. Out of 143,554 mined rules, 60,997 were related to corrosion failures, while only 6 were related to operation failures. Compared to traditional methods, the TAFP-Growth algorithm demonstrates higher efficiency and reliability in processing industrial data, providing a fast and reliable solution for analyzing failure patterns. This method provides significant support for improving management and decision-making in the oil industry.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"264 ","pages":"Article 111281"},"PeriodicalIF":9.4,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144205362","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