Yan Han , Ailin Hu , Qingqing Huang , Yan Zhang , Zhichao Lin , Jinghua Ma
{"title":"Sinkhorn divergence-based contrast domain adaptation for remaining useful life prediction of rolling bearings under multiple operating conditions","authors":"Yan Han , Ailin Hu , Qingqing Huang , Yan Zhang , Zhichao Lin , Jinghua Ma","doi":"10.1016/j.ress.2024.110557","DOIUrl":"10.1016/j.ress.2024.110557","url":null,"abstract":"<div><div>Under multiple operating conditions, the degradation characteristics of rolling bearings show diverse distributions. Domain adaptation (DA) achieves effective alignment between source and target domains by extracting domain-invariant features. However, in the prediction of remaining useful life (RUL) for bearings, numerous DA methods overlook mutual information from target-specific data and encounter potential challenges such as the vanishing gradient problem during the alignment of data distributions, leading to limited performance. To address these challenges, a novel method called Sinkhorn Divergence-based Contrast Domain Adaptation (SD_CDA) is proposed to predict RUL under multiple operating conditions. Firstly, an adversarial training framework is constructed to initially extract domain-invariant features. Subsequently, the cross-domain temporal mixup strategy is proposed for the data augment, which obtains positive samples to serve contrastive learning. Then self-supervised momentum contrast (MoCo) is employed to extract mutual information from target-specific data, preserving its specificity. Finally, Sinkhorn divergence is introduced to further align the fine-grained structure of the source domain and target domain, and enhance the transfer ability of the model. The experimental results demonstrate the superiority and effectiveness of the proposed method under multiple operating conditions.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"253 ","pages":"Article 110557"},"PeriodicalIF":9.4,"publicationDate":"2024-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142420989","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":"Assessment of corrosion probability of steel in mortars using machine learning","authors":"Haodong Ji, Yuhui Lyu, Zushi Tian, Hailong Ye","doi":"10.1016/j.ress.2024.110535","DOIUrl":"10.1016/j.ress.2024.110535","url":null,"abstract":"<div><div>Corrosion assessment enables engineers to quickly discern the corrosion status of steel in concrete structures. However, existing assessment methods mainly rely on a single-factor and exhibit poor adaptability to various corrosion scenarios. Moreover, most methods are traditional deterministic approach, which ignores the uncertainties in corrosion assessments. In this work, machine learning (ML) is employed to develop a multifactor classification model for multi-level corrosion status assessment, together with corresponding corrosion probability maps. First, a comprehensive corrosion dataset was collected, including relative humidity (RH), electrical resistivity (ER), corrosion potential (CP), and corrosion rate (CR). The CR was used to subdivide different corrosion levels, and ML classification models were established for three-factor and two-factor scenarios. The optimal model was then used to create corrosion probability maps for various corrosion levels. The results indicated that the poor reliability and accuracies in current corrosion assessment methods originated from the inconsistent corrosion behaviors induced by carbonation and chloride in concrete. Moreover, when using the corrosion probability maps to assess corrosion status of steel in mortars, CP and ER should first be used to determine if the steel is in an active state, followed by RH and CP to evaluate whether it is in a severe-corrosion state.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"253 ","pages":"Article 110535"},"PeriodicalIF":9.4,"publicationDate":"2024-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142421440","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":"Wind turbine fault detection and identification via self-attention-based dynamic graph representation learning and variable-level normalizing flow","authors":"Yunyi Zhu , Bin Xie , Anqi Wang , Zheng Qian","doi":"10.1016/j.ress.2024.110554","DOIUrl":"10.1016/j.ress.2024.110554","url":null,"abstract":"<div><div>Effective wind turbine (WT) condition monitoring is significant to improve wind power generation efficiency and reduce operation and maintenance costs. Supervisory control and data acquisition (SCADA) data are widely utilized for WT condition monitoring due to their low cost and accessibility. However, the intricate interdependencies among SCADA variables affect the accuracy of WT fault detection, and few methods provide identification for the anomaly cause. To solve these issues, this paper proposes an unsupervised fault detection and identification method based on self-attention-based dynamic graph representation learning and variable-level normalizing flow. Firstly, a dynamic graph representation learning model based on spatial and temporal self-attention mechanisms is proposed. It can effectively learn the dynamic and mutual relations among variables for early fault detection. Secondly, a variable-level normalizing flow is proposed for discriminative density estimation of variables, which can realize component fault localization. Finally, a node deviation index based on contrast graph is proposed to identify the root cause of anomalies. Experimental results using WT data from a wind farm in Northwest China prove that the proposed method has better accuracy and interpretability in WT fault detection and identification, which displays better effectiveness in practical wind energy applications.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"253 ","pages":"Article 110554"},"PeriodicalIF":9.4,"publicationDate":"2024-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142420985","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}
Ruihan Wang , Mingyang Zhang , Fuzhong Gong , Shaohan Wang , Ran Yan
{"title":"Improving port state control through a transfer learning-enhanced XGBoost model","authors":"Ruihan Wang , Mingyang Zhang , Fuzhong Gong , Shaohan Wang , Ran Yan","doi":"10.1016/j.ress.2024.110558","DOIUrl":"10.1016/j.ress.2024.110558","url":null,"abstract":"<div><div>With the advancements in modern information technology, Port State Control (PSC) inspections, as a crucial measure to protect ship safety and the marine environment, are undergoing an intelligent transformation. This paper aims to streamline the selection process for inspecting high-risk ships by employing a data-driven model to predict the number of deficiencies in ships arriving at ports. A transfer learning-enhanced eXtreme Gradient Boosting (XGBoost) model is proposed by innovatively incorporating sample similarity calculations to adapt the model to the unique characteristics of the target port. This novel model enables the integration of relevant data from other ports, enhancing the predictive performance of the model to specific port conditions. Utilizing PSC inspection records from ports within the Tokyo Memorandum of Understanding (MoU) and choosing the port of Singapore as the target, numerical experiments demonstrate that the proposed model achieves improvements of 1.81 %, 6.08 %, and 3.60 % in the mean absolute error, mean squared error and root mean squared error, respectively, compared to the standard XGBoost model. Furthermore, across various sizes of training samples, the proposed model outperforms other machine learning models. This work may service as a significant step towards exploring the potential of developing data-driven models based on comprehensive data to assess the risk level of foreign ships arriving at ports, ameliorating the PSC inspection process by aiding PSC officers in identifying substandard ships more effectively.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"253 ","pages":"Article 110558"},"PeriodicalIF":9.4,"publicationDate":"2024-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142421569","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":"Prediction model optimization of gas turbine remaining useful life based on transfer learning and simultaneous distillation pruning algorithm","authors":"Yu Zheng, Liang Chen, Xiangyu Bao, Fei Zhao, Jingshu Zhong, Chenhan Wang","doi":"10.1016/j.ress.2024.110562","DOIUrl":"10.1016/j.ress.2024.110562","url":null,"abstract":"<div><div>For the application of deep learning (DL) models in the field of remaining useful life (RUL) prediction and predictive maintenance (PdM) of complex equipment, the insufficient training data and large model are the two major problems. To address these issues, a model training method based on transfer learning and a simultaneous distillation pruning algorithm were proposed. By introducing prior knowledge, three transfer learning modes are devised to reduce the demand of training data. Additionally, the simultaneous distillation pruning algorithm was devised to make the model lightweight, and an iterative pruning method was adopted to trim the large neural network model. By analyzing the performance of different transfer learning modes, the effectiveness of the proposed method can be demonstrated. The number of model parameters and the performance before and after pruning were compared. The results demonstrated that, without significant alterations to the prediction performance, the proposed model exhibited the capability to markedly reduce the number of model parameters. Based on the proposed methods, the challenges of insufficient data and efficiency encountered by DL models could be effectively addressed.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"253 ","pages":"Article 110562"},"PeriodicalIF":9.4,"publicationDate":"2024-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142420995","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}
Yuanyuan Guo , Youchao Sun , Qingmin Si , Xinyao Guo , Nongtian Chen
{"title":"Probabilistic risk assessment of civil aircraft associated failures under condition-based maintenance","authors":"Yuanyuan Guo , Youchao Sun , Qingmin Si , Xinyao Guo , Nongtian Chen","doi":"10.1016/j.ress.2024.110550","DOIUrl":"10.1016/j.ress.2024.110550","url":null,"abstract":"<div><div>Maintenance can improve an aircraft system's reliability over a long operation period or when a component has failed. However, inappropriate maintenance inspection intervals will cause latent failures to be covered or undetected, leading to a large number of unplanned flight disruptions for airlines. In this paper, we present a two-stage framework to assess the associated failure risk of civil aircraft under condition-based maintenance. In the first stage of the framework, the probability of primary functional failure across the lifecycles of the monitored component is determined by analyzing whether the current inspection interval prevents the component from progressing from latent failure to functional failure. In the second stage of the framework, the associated failure probability between components and related systems is formulated by the adjacency matrix. The structure and performance of the proposed model were tested on a case study by run-to-failure data associated with aircraft engines from a large airline. Focusing on the scenario of turbine disk cracking leading to fragment penetration of the fuel tank and causing fire as the consequential fault impact path, the results show that the risk of aircraft fire caused by turbine disk fragments falls within an acceptable range, necessitating the completion of inspections and subsequent monitoring within the stipulated timeframe. The method can be used to readjust the inspection interval, optimize the operation plan, improve the on-time performance of flights, and reduce the risk of aviation accidents.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"253 ","pages":"Article 110550"},"PeriodicalIF":9.4,"publicationDate":"2024-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142421436","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":"An ontology-based multi-hazard coupling accidents simulation and deduction system for underground utility tunnel - A case study of earthquake-induced disaster chain","authors":"Yin Gu, Chenyang Wang, Yi Liu, Rui Zhou","doi":"10.1016/j.ress.2024.110559","DOIUrl":"10.1016/j.ress.2024.110559","url":null,"abstract":"<div><div>Integrated underground utility tunnels are increasingly crucial in modern cities, addressing the pressing need for sustainable urban development. However, their extensive centralization amplifies both the complexity and scale of potential risks. When a utility tunnel accident occurs, it is possible to trigger a sequence of cascading events, thereby resulting a complex coupling accident. While previous research has predominantly focused on individual hazards, understanding multi-hazard coupling accidents presents significant challenges and lacks effective methodologies. In this paper, we propose an integrated system utilizing ontology technology and knowledge base construction for simulating and deducing coupling accidents in urban utility tunnels. Specifically, by extending ontology techniques to emergency decision-making and adopting the triangular framework for public safety, we establish a multidimensional information ontology for utility tunnel emergencies. Furthermore, a knowledge base for typical coupling accident evolution paths is established based on the event chain and contingency plan chain theory. Through integration with a multi-hazard accident basic database that serves the conditional, investigative and decision-making node within the evolution path, the simulation and deduction system is formulated, boasting a user-friendly visual interface, interactive functionality, and seamless applicability for widespread adoption. A case study demonstrates the system ability to support multiple paths and unified mapping deduction, offering practical emergency decision-making suggestions to mitigate cascading events in urban utility tunnels.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"253 ","pages":"Article 110559"},"PeriodicalIF":9.4,"publicationDate":"2024-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142530322","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}
Dequan Zhang, Hongyi Liang, Xing-ao Li, Xinyu Jia, Fang Wang
{"title":"Kinematic calibration of industrial robot using Bayesian modeling framework","authors":"Dequan Zhang, Hongyi Liang, Xing-ao Li, Xinyu Jia, Fang Wang","doi":"10.1016/j.ress.2024.110543","DOIUrl":"10.1016/j.ress.2024.110543","url":null,"abstract":"<div><div>Positioning accuracy of an end-effector is a crucial metric for evaluating industrial robot performance. Uncertainties in joint angles and joint backlash deviate actual angles from the designed nominal values to negate positioning accuracy. Most existing parameter identification methods overlook or not properly account for such uncertainties, leading to usually overconfident identification results. To this gap, the present study introduces a kinematic calibration methodology employing Bayesian parameter estimation to achieve identification of joint variables. New formulas based on data features of industrial robots for constructing the likelihood function are proposed, and model selection is applied to assess various likelihood functions for a tradeoff balance between complexity and accuracy. To evaluate the robustness of the proposed approach, identification of joint variables is conducted under different measurement noises. The position response of kinematic model is predicted based on the identified joint uncertainty information. The efficacy is verified through rigorous scrutiny involving both a numerical example and an engineering application. Results indicate that the proposed method exhibits satisfactory kinematic parameter identification accuracy and robustness. In addition, the uncertainty of parameters can be measured and the prediction of trajectory uncertainty intervals is realized simultaneously, which promotes the application of industrial robots in high-precision scenes.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"253 ","pages":"Article 110543"},"PeriodicalIF":9.4,"publicationDate":"2024-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142530314","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}
Haiming Jiao , Zhen Hu , Zhijiang Yang , Wen Zeng , Feng Xu , Cuiyan Han
{"title":"Hierarchical structure-based model for importance and reliability assessment of water distribution networks","authors":"Haiming Jiao , Zhen Hu , Zhijiang Yang , Wen Zeng , Feng Xu , Cuiyan Han","doi":"10.1016/j.ress.2024.110542","DOIUrl":"10.1016/j.ress.2024.110542","url":null,"abstract":"<div><div>The Segment-Valve (SV) model can be utilized to analyze the reliability of water distribution networks (WDNs). However, it often focuses on the impact of segment failures on themselves. The isolation of segments in the WDNs not only affects the segments themselves but also influences other segments through which the water supply path passes. Therefore, considering the water supply path and the interaction between upstream and downstream segments, we convert the loops in the SV graph to nodes to simplify them, clearly describing the segmented hierarchy and its interconnections in a tree-like form, termed SV-tree. Based on the SV-tree and complex network theory, a method is proposed to estimate the supply shortage rate using betweenness centrality to provide a detailed analysis for local importance on example WDNs. Meanwhile, new analysis indicators that can reflect the global reliability of the WDNs are constructed from the mutual influence between segments and the difficulty for users to obtain water. The results demonstrate the efficacy of the new importance assessment indicator across various WDNs configurations, and its calculation time is much lower than that of hydraulic simulation. In addition, the reliability assessment indicators are more practical and can effectively identify problems existing in the WDNs.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"253 ","pages":"Article 110542"},"PeriodicalIF":9.4,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142421434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Gyeongho Kim , Yun Seok Kang , Sang Min Yang , Jae Gyeong Choi , Gahyun Hwang , Hyung Wook Park , Sunghoon Lim
{"title":"Fisher-informed continual learning for remaining useful life prediction of machining tools under varying operating conditions","authors":"Gyeongho Kim , Yun Seok Kang , Sang Min Yang , Jae Gyeong Choi , Gahyun Hwang , Hyung Wook Park , Sunghoon Lim","doi":"10.1016/j.ress.2024.110549","DOIUrl":"10.1016/j.ress.2024.110549","url":null,"abstract":"<div><div>Accurate prediction of remaining useful life (RUL) of equipment has become an essential task in manufacturing. It not only helps prevent unexpected failures but also enables maximal utilization of available life, thus improving process efficiency. In practice, however, the use of multiple operating conditions that vary by time impedes efficient data-driven RUL prediction. Unlike conventional supervised learning setups, varying operating conditions generate heterogeneous data with time-varying generating distributions. Thus, existing approaches cannot be effectively applied due to increasing modeling and memory costs. One of the domains that suffer from this issue is machining, where RUL prediction of cutting tools is crucial for productivity. Considering realistic circumstances with varying operating conditions, this work proposes a method named Fisher-informed continual learning (FICL), which enables efficient tool RUL prediction that adaptively learns as conditions change without storing previous data and models. FICL uses Fisher information to improve generalization via sharpness-aware minimization and transfer knowledge between operating conditions through structural regularization. Experiments using datasets from real-world machining processes under five distinct operating conditions prove FICL’s efficacy, indicating its superior prediction performance to existing methods for all operating conditions. Particularly, FICL manifests the least catastrophic forgetting, implying it effectively retains informative knowledge from varying operating conditions.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"253 ","pages":"Article 110549"},"PeriodicalIF":9.4,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142442858","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}