Reliability Engineering & System Safety最新文献

{"title":"Knowledge-informed FIR-based cross-category filtering framework for interpretable machinery fault diagnosis under small samples","authors":"Rui Liu ,&nbsp;Xiaoxi Ding ,&nbsp;Shenglan Liu ,&nbsp;Hebin Zheng ,&nbsp;Yuanyaun Xu ,&nbsp;Yimin Shao","doi":"10.1016/j.ress.2024.110610","DOIUrl":"10.1016/j.ress.2024.110610","url":null,"abstract":"<div><div>Relying on sufficient training data, the existing fault diagnosis methods rarely focus on the methodological interpretability and the data scarcity in real industrial scenarios simultaneously. Motivated by this issue, we deeply reexamined the intrinsic characteristics of fault signals and the guiding significance of classical signal-processing methods for feature enhancement. From the perspective of multiscale modes, this study tailors multiple learnable knowledge-informed finite impulse response (FIR) filtering kernels to extract sensitive modes for explainable feature enhancement. On this foundation, a knowledge-informed FIR-based cross-category filtering (FIR-CCF) framework is further proposed for interpretable small-sample fault diagnosis. With the consideration of the mode complexity, a cross-category filtering strategy is explored to further enhance feature expressions for identifying single state. To be special, this strategy divides a multi-class recognition process into multiple two-class recognition task. A multi-task learning is then presented where multiple binary-class base learners (BCBLearners) that consists of a feature extractor and a two-class classifier is established to seek discriminate mode features for each type of state. Eventually, all feature extractors are fixed and a multi-class classifier is established and to fuse all mode features for high-precision multi-class identification via ensemble learning. As a variant of signal-processing-collaborated deep learning frameworks, the FIR-CCF method fully exploits the strengths of signal-processing methods in interpretability and feature extraction. Three experimental cases highlight the superiority and significant improvement of the FIR-CCF framework over other five state-of-the-art diagnosis methods and three ablation models. Specially, extensive visualization is implemented to place in-depth insight into how the FIR-CCF framework works. It can be also foreseen that the signal-processing-collaborated deep learning framework shows enormous potential in interpretable fault diagnosis for knowledge-informed artificial intelligence. Related source codes will be available at: <span><span>https://github.com/BITS/FIR-CCF-main</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"254 ","pages":"Article 110610"},"PeriodicalIF":9.4,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142657440","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":"Physics-informed machine learning for system reliability analysis and design with partially observed information","authors":"Yanwen Xu ,&nbsp;Parth Bansal ,&nbsp;Pingfeng Wang ,&nbsp;Yumeng Li","doi":"10.1016/j.ress.2024.110598","DOIUrl":"10.1016/j.ress.2024.110598","url":null,"abstract":"<div><div>Constructing a high-fidelity predictive model is crucial for analyzing complex systems, optimizing system design, and enhancing system reliability. Although Gaussian Process (GP) models are well-known for their capability to quantify uncertainty, they rely heavily on data and necessitate a large representative dataset to establish a high-fidelity predictive model. Physics-informed Machine Learning (PIML) has emerged as a way to integrate prior physics knowledge and machine learning models. However, current PIML methods are generally based on fully observed datasets and mainly suffer from two challenges: (1) effectively utilize partially available information from multiple sources of varying dimensions and fidelity; (2) incorporate physics knowledge while maintaining the mathematical properties of the GP-based model and uncertainty quantification capability of the predictive model. To overcome these limitations, this paper proposes a novel physics-informed machine learning method that incorporates physics prior knowledge and multi-source data by leveraging latent variables through the Bayesian framework. This method effectively utilizes partially available limited information, significantly reduces the need for costly fully observed data, and improves prediction accuracy while maintaining the model property of uncertainty quantification. The developed approach has been demonstrated with two case studies: the vehicle design problem and the battery capacity loss prediction. The case study results demonstrate the effectiveness of the proposed model in complex system design and optimization while propagating uncertainty with limited fully observed data.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"254 ","pages":"Article 110598"},"PeriodicalIF":9.4,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142657362","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":"Employing the cluster of node cut sets to improve the robustness of the network measured by connectivity","authors":"Wei Wei,&nbsp;Guobin Sun,&nbsp;Peng Li,&nbsp;Qinghui Zhang","doi":"10.1016/j.ress.2024.110612","DOIUrl":"10.1016/j.ress.2024.110612","url":null,"abstract":"<div><div>Protection of critical nodes or edges can help defend networks from failures caused by natural disasters or intended attacks. Node protection becomes the only way when edge protection is not possible, where node connectivity is usually used to measure network robustness due to its effectiveness. Although simple, node connectivity-oriented node consolidation optimization is still NP-hard, especially when dealing with large numbers of nodes. To address the problem, by leveraging the mapping between nodes and traversal trees, per-node cluster of node cut sets is used to identify nominee nodes, which are then conditionally consolidated through a extended dual tree-based selection process. Experimental results show that in small graphs with tens of nodes where the optimal algorithm is applicable, an acceleration ratio of more than <span><math><mrow><mn>1</mn><msup><mrow><mn>0</mn></mrow><mrow><mn>5</mn></mrow></msup></mrow></math></span> (at most <span><math><mrow><mn>1</mn><msup><mrow><mn>0</mn></mrow><mrow><mn>6</mn></mrow></msup></mrow></math></span>) is observed at the expense of about 6% extra cost. In large graphs with millions of nodes, the proposed algorithm can help promote node connectivity of more than 99.9% of node pairs, which is far better than commonly used heuristics. Its inherent ready-for-paralleling capability paves the way for more speedups.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"254 ","pages":"Article 110612"},"PeriodicalIF":9.4,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142586200","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":"Distribution reconstruction and reliability assessment of complex LSFs via an adaptive Non-parametric Density Estimation Method","authors":"Quanfu Yu ,&nbsp;Jun Xu","doi":"10.1016/j.ress.2024.110609","DOIUrl":"10.1016/j.ress.2024.110609","url":null,"abstract":"<div><div>Complex limit state functions (LSFs), often characterized by strong nonlinearity, non-smoothness, or discontinuity, pose challenges for structural reliability analysis in engineering practices. Conventional methods for uncertainty propagation and reliability assessment may struggle to handle these issues effectively. This paper introduces a novel approach to adaptively reconstruct the unknown distributions of complex LSFs. The Non-parametric Density Estimation Method based on Harmonic Transform (NDEM-HT) is employed as the tool for this purpose. An adaptive strategy is then proposed to determine the number of harmonic moments required in NDEM-HT for achieving high accuracy. Specifically, the Adaptive Kernel Density Estimation (AKDE) method is also adopted to provide an initial estimation of the rough distribution. Subsequently, the optimal number of harmonic moments is determined by minimizing the relative entropy between the distributions obtained by AKDE and NDEM-HT. The efficacy of the proposed method is demonstrated through five numerical examples, considering various types of complex LSFs. Comparative results are also provided employing MCS along with both conventional and state-of-the-art methods.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"254 ","pages":"Article 110609"},"PeriodicalIF":9.4,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142657358","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":"Health management of power batteries in low temperatures based on Adaptive Transfer Enformer framework","authors":"Bingyang Chen ,&nbsp;Xingjie Zeng ,&nbsp;Chao Liu ,&nbsp;Yafei Xu ,&nbsp;Heling Cao","doi":"10.1016/j.ress.2024.110613","DOIUrl":"10.1016/j.ress.2024.110613","url":null,"abstract":"<div><div>Accurate State of Charge (SOC) estimation is essential for extending battery life and improving the safety of battery management systems. However, many existing methods face challenges, including a lack of sufficient samples in specific driving modes, overlooking hidden factors such as low temperatures, and experiencing negative transfer in transfer learning. This paper introduces the Adaptive Transfer Enformer (ATE) Framework, which integrates an Enhanced Transformer (Enformer) model with Adaptive Transfer Learning (ATL). The Enformer incorporates Multilevel Residual Attention (MRA) and Pattern Dynamic Decomposition (PDD), forming the backbone of the pre-trained model. MRA addresses gradient vanishing issues due to limited samples and captures the underlying relationships at each time point. PDD dynamically learns temporal trends, hidden factors, and their interactions. ATL provides an effective feature learning strategy to promote positive transfer in SOC estimation. Experimental results on two public datasets with added noise show that the proposed method improves average accuracy compared to state-of-the-art methods. Additionally, results from nine transfer scenarios demonstrate the strong generalization and noise resistance capabilities of the ATE Framework.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"254 ","pages":"Article 110613"},"PeriodicalIF":9.4,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593304","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":"Preventive maintenance strategy for multi-component systems in dynamic risk assessment","authors":"Chengjie Zhang,&nbsp;Zhigeng Fang,&nbsp;Wenjie Dong","doi":"10.1016/j.ress.2024.110611","DOIUrl":"10.1016/j.ress.2024.110611","url":null,"abstract":"<div><div>As the system operates, the system risk level will also dynamically change. In this paper, a dynamic risk assessment of the system is carried out by considering the system reliability and system risk losses, both of which vary over time. Then, based on the system risk level, different maintenance measures are applied to the components that have reached the preventive maintenance thresholds, including medium repair, major repair, and replacement. If the system risk is relatively light, low-cost medium repair will be adopted to save maintenance resources. Thus, a novel maintenance optimization strategy for multi-component systems considering the system risk level and aiming to minimize maintenance costs is proposed. Finally, the feasibility and effectiveness of the model are verified through a numerical case of the air conditioning temperature regulation subsystem.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"254 ","pages":"Article 110611"},"PeriodicalIF":9.4,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142578691","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 reliability health status assessment model for complex systems based on belief rule base","authors":"Mingyuan Liu,&nbsp;Wei He,&nbsp;Ning Ma,&nbsp;Hailong Zhu,&nbsp;Guohui Zhou","doi":"10.1016/j.ress.2024.110614","DOIUrl":"10.1016/j.ress.2024.110614","url":null,"abstract":"<div><div>In complex systems, health status assessment identifies system conditions and potential issues. However, large uncertainties and variations make efficient model construction challenging. The belief rule base (BRB), which addresses uncertainty through data-driven and knowledge-driven methods, is widely used for health status assessment of complex systems. Current BRB modeling methods focus primarily on accuracy, leaving a gap in research on reliability. Therefore, a reliable BRB (RE-BRB), which enables effective modeling for complex system health assessment under high reliability requirements, is proposed in this paper. First, a systematic reliability analysis of the BRB is performed, and the reliability criteria are defined. Second, the model parameters of the RE-BRB are optimized via the nondominated sorting whale optimization algorithm with reliability constraints (NSWOA), and the reliability of the model is ensured. In addition, a perturbation analysis of the RE-BRB model is conducted to identify the perturbation thresholds. The perturbation thresholds acceptable to the model provide guidance for managers in making decisions. Last, using the WD615 diesel engine and flywheel bearing as examples, this method achieves reliable system health status assessment by accurately assessing system status, incorporating the ability to address external perturbations and providing an easily interpretable output process.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"254 ","pages":"Article 110614"},"PeriodicalIF":9.4,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142578692","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":"Toward the resilience of UAV swarms with percolation theory under attacks","authors":"Tianzhen Hu ,&nbsp;Yan Zong ,&nbsp;Ningyun Lu ,&nbsp;Bin Jiang","doi":"10.1016/j.ress.2024.110608","DOIUrl":"10.1016/j.ress.2024.110608","url":null,"abstract":"<div><div>Unmanned aerial swarms have been widely applied across various domains. The security of swarms against attacks has been of significance. However, there still exists a lack of quantitatively assessing the unmanned swarm resilience against attacks. Thus, this work adopts the percolation theory to mathematically analyse the resilience of the unmanned aerial swarms after random attacks. In addition to the typically used popularity in the preferential attachment, distance of neighbours is taken into account for modelling unmanned swarms, which is missing in the literature. This improved preferential attachment-based swarm model offers a more precise and realistic description of swarm behaviours. In addition, an attack model is proposed, which can be a description of dynamic attacks. Moreover, this study also utilizes the percolation theory to assess the resilience of swarms after the random attacks. Finally, the simulation results show that the resilience derived using percolation theory aligns with the improved swarm model. The proposed swarm model maintains <span><math><mrow><mn>79</mn><mtext>%</mtext></mrow></math></span> resilience when <span><math><mrow><mn>20</mn><mtext>%</mtext></mrow></math></span> of the UAVs are attacked under random attacks, and even <span><math><mrow><mn>69</mn><mo>.</mo><mn>4</mn><mtext>%</mtext></mrow></math></span> resilience when <span><math><mrow><mn>20</mn><mtext>%</mtext></mrow></math></span> of the UAVs are attacked under initial betweenness-based attacks.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"254 ","pages":"Article 110608"},"PeriodicalIF":9.4,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142586201","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":"Reliability evaluation for a multi-commodity multi-state distribution network under transportation emission consideration","authors":"Yi-Feng Niu ,&nbsp;Jun-Feng Wang ,&nbsp;Xiu-Zhen Xu ,&nbsp;Qian-Xin Xu","doi":"10.1016/j.ress.2024.110599","DOIUrl":"10.1016/j.ress.2024.110599","url":null,"abstract":"<div><div>This study, from the perspective of environmental effect, presents a novel reliability evaluation of a multi-commodity multi-state distribution network (MMDN) with consideration of transportation emission, in which a node stands for a supplier, a distribution center or a market, an arc represents a carrier offering transportation service along that arc, and multiple types of commodities are simultaneously transported from several sources to the destination. Due to the existence of unpredictable events, the available capacity of each arc should be multi-state, thus, network reliability under transportation emission consideration, defined as the probability that a specific amount of multiple types of commodities can be successfully distributed from several sources to the destination while the carbon emissions generated by all vehicles are within a limit, can serve as a valuable reference to assess the ability of an MMDN to complete the delivery task with limited environmental impact. An algorithm, using minimal paths vectors (MPVs), is proposed to evaluate the indicator, and the solution steps are explicated through an example network. Additionally, a case study is explored to indicate the practicality of the new reliability index and calculation method.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"254 ","pages":"Article 110599"},"PeriodicalIF":9.4,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593305","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":"Identification of reference security scenarios from past event datasets by Bayesian Network analysis","authors":"Matteo Iaiani,&nbsp;Giuseppe Fazari,&nbsp;Alessandro Tugnoli,&nbsp;Valerio Cozzani","doi":"10.1016/j.ress.2024.110615","DOIUrl":"10.1016/j.ress.2024.110615","url":null,"abstract":"<div><div>The global threat of deliberate attacks on chemical, process, and energy facilities underscores the urgent need to enhance Security Vulnerability/Risk Assessment (SVA/SRA) approaches. Traditional assessments often use historical data and Exploratory Data Analysis (EDA) to identify reference scenarios. However, EDA lacks a standardized approach to identify and rank the incident chains. A novel methodology based on Bayesian Networks (BN), named BAS²E, was developed to support the systematic identification of reference scenarios from past event datasets. The methodology is based on the development of a static quantified BN, that accurately reflects the causal relationships in incident chains, focusing specifically on those between threats, attack methods, and physical damage scenarios. The BN is quantified by statistical information from the analysis of the incident records and employs the Noisy-OR gate model to manage data gaps in the conditional probability tables (CPTs) specification. The application of the BN sensitivity analysis provides quantification of the reciprocal influence between nodes using a specific derivative-based parameter, allowing for the systematic ranking of the most impactful incident chains to be included as reference scenarios in SVA/SRA. The methodology is demonstrated through its application to a dataset of 109 security incidents that occurred in the offshore Oil&amp;Gas sector.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":"254 ","pages":"Article 110615"},"PeriodicalIF":9.4,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142657355","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}