Reliability Engineering & System Safety最新文献_第4页

Research on Scenario Extrapolation and Emergency Decision-Making for Fire and Explosion Accidents at University Laboratories Based on BN-CBR 基于 BN-CBR 的大学实验室火灾和爆炸事故情景推断与应急决策研究

IF 9.4 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Reliability Engineering & System Safety

Pub Date : 2024-10-10 DOI: 10.1016/j.ress.2024.110579

To solve the problems of suddenness, uncertainty and untimely emergency decision-making related to fire and explosion accidents in university laboratories, a combined method of BN and CBR is introduced to analyze laboratory accidents. By summarizing the characteristics of 72 accident cases worldwide, four scenario elements with key roles are extracted by combining the public safety triangle theoretical model; a BN is established from the macro perspective, which is based on the construction of dynamic scenarios; the evolution path is analyzed via BN theory; and the probability of occurrence of accidents is quantified from the microscopic perspective, with a focus on the analysis of the accidental evolution process. A case similarity calculation is carried out via CBR, and the construction of a BN-CBR-assisted decision-making model is completed, verified and corrected in an case study. The results show that the BN-CBR model can quickly determine the accident evolution path and the most similar historical cases, and its quantitative probability calculation enables one to comprehensively grasp the real-time state of the whole accident and the emergency response in a timely manner, which provides a new way to approach emergency decision-making of accidents.

为解决高校实验室火灾爆炸事故的突发性、不确定性和应急决策不及时等问题，引入BN和CBR相结合的方法对实验室事故进行分析。通过总结全球 72 起事故案例的特点，结合公共安全三角理论模型，提取了四个具有关键作用的情景要素；从宏观角度建立了基于动态情景构建的 BN；通过 BN 理论分析了演化路径；从微观角度量化了事故发生概率，重点分析了事故演化过程。通过 CBR 进行案例相似性计算，在案例研究中完成 BN-CBR 辅助决策模型的构建、验证和修正。结果表明，BN-CBR模型能够快速确定事故演化路径和最相似的历史案例，其定量概率计算能够及时全面地掌握整个事故的实时状态和应急响应，为事故应急决策提供了新的思路。

{"title":"Research on Scenario Extrapolation and Emergency Decision-Making for Fire and Explosion Accidents at University Laboratories Based on BN-CBR","authors":"","doi":"10.1016/j.ress.2024.110579","DOIUrl":"10.1016/j.ress.2024.110579","url":null,"abstract":"<div><div>To solve the problems of suddenness, uncertainty and untimely emergency decision-making related to fire and explosion accidents in university laboratories, a combined method of BN and CBR is introduced to analyze laboratory accidents. By summarizing the characteristics of 72 accident cases worldwide, four scenario elements with key roles are extracted by combining the public safety triangle theoretical model; a BN is established from the macro perspective, which is based on the construction of dynamic scenarios; the evolution path is analyzed via BN theory; and the probability of occurrence of accidents is quantified from the microscopic perspective, with a focus on the analysis of the accidental evolution process. A case similarity calculation is carried out via CBR, and the construction of a BN-CBR-assisted decision-making model is completed, verified and corrected in an case study. The results show that the BN-CBR model can quickly determine the accident evolution path and the most similar historical cases, and its quantitative probability calculation enables one to comprehensively grasp the real-time state of the whole accident and the emergency response in a timely manner, which provides a new way to approach emergency decision-making of accidents.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":null,"pages":null},"PeriodicalIF":9.4,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142420980","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

Emergency evacuation risk assessment for toxic gas attacks in airport terminals: Model, algorithm, and application 机场航站楼有毒气体袭击的紧急疏散风险评估：模型、算法和应用

IF 9.4 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Reliability Engineering & System Safety

Pub Date : 2024-10-10 DOI: 10.1016/j.ress.2024.110576

Transportation infrastructure has often been the target of terrorist attacks, and mitigation of the risk of toxic gas attacks is a challenging task in the design of indoor emergency evacuation systems. Considering multiple emergency response modes, we propose an agent-based risk assessment model and its algorithm to integrate gas diffusion and pedestrian movement data for emergency response, quickly assessing average individual exposure risk. We assessed the exposure status of individuals with respect to their emergency response actions following a toxic gas attack in an airport terminal. The results indicate that in the event of a general gas attack on an airport terminal, ventilation must be immediately ceased along with early evacuation. In areas with a shelter-in-place environment, the ventilation mode and shelter-in-place time should be determined based on the concentration of indoor and outdoor gases. In areas with nerve gas exposure and high population density, a new exit must be established at evacuation bottlenecks, and pedestrians must be guided to evacuate while promptly closing ventilation. These results offer suggestions and strategies for emergency response and decision-making in airport terminals during such incidents.

交通基础设施经常成为恐怖袭击的目标，而降低有毒气体袭击的风险是室内紧急疏散系统设计中的一项具有挑战性的任务。考虑到多种应急响应模式，我们提出了一种基于代理的风险评估模型及其算法，用于整合应急响应中的气体扩散和行人移动数据，快速评估个人平均暴露风险。在机场航站楼发生有毒气体袭击事件后，我们评估了个人在应急响应行动中的暴露状况。结果表明，在机场航站楼发生一般毒气袭击时，必须立即停止通风并尽早疏散。在有就地掩蔽环境的区域，应根据室内外气体浓度确定通风模式和就地掩蔽时间。在神经毒气暴露区和人口密集区，必须在疏散瓶颈处设立新的出口，在及时关闭通风的同时引导行人疏散。这些结果为机场航站楼在此类事件中的应急响应和决策提供了建议和策略。

{"title":"Emergency evacuation risk assessment for toxic gas attacks in airport terminals: Model, algorithm, and application","authors":"","doi":"10.1016/j.ress.2024.110576","DOIUrl":"10.1016/j.ress.2024.110576","url":null,"abstract":"<div><div>Transportation infrastructure has often been the target of terrorist attacks, and mitigation of the risk of toxic gas attacks is a challenging task in the design of indoor emergency evacuation systems. Considering multiple emergency response modes, we propose an agent-based risk assessment model and its algorithm to integrate gas diffusion and pedestrian movement data for emergency response, quickly assessing average individual exposure risk. We assessed the exposure status of individuals with respect to their emergency response actions following a toxic gas attack in an airport terminal. The results indicate that in the event of a general gas attack on an airport terminal, ventilation must be immediately ceased along with early evacuation. In areas with a shelter-in-place environment, the ventilation mode and shelter-in-place time should be determined based on the concentration of indoor and outdoor gases. In areas with nerve gas exposure and high population density, a new exit must be established at evacuation bottlenecks, and pedestrians must be guided to evacuate while promptly closing ventilation. These results offer suggestions and strategies for emergency response and decision-making in airport terminals during such incidents.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":null,"pages":null},"PeriodicalIF":9.4,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142530318","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

Remaining useful life prediction of nuclear reactor control rod drive mechanism based on dynamic temporal convolutional network 基于动态时序卷积网络的核反应堆控制棒驱动机构剩余使用寿命预测

IF 9.4 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Reliability Engineering & System Safety

Pub Date : 2024-10-10 DOI: 10.1016/j.ress.2024.110580

The control rod drive mechanism (CRDM) is a critical equipment of the nuclear reactor, and the prediction of its remaining useful life (RUL) is important for the efficient maintenance and ensuring the safe, reliable operation of nuclear power plants. In this paper, a novel framework for the RUL prediction of CRDM is proposed, which is a dynamic temporal convolution network (DTCN) based on dynamic activation function and attention mechanism. Firstly, the temporal convolution network (TCN) is used as the backbone of the prediction model, to extract the temporal dependence of the input data. Next, the dynamic activation function DReLU is integrated into the TCN, which can dynamically activate features and capture variable degradation information. Then, introducing the attention mechanism improves the influence of important high-level features extracted by the network on RUL prediction, thereby improving the efficiency of feature extraction in the network. Finally, the DTCN outputs the predicted RUL by performing non-linear mapping on the extracted features. The CRDM accelerated life test platform is established and a series of experiments are conducted using the collected CRDM full-life vibration dataset. The results demonstrated the performance and advantages of the proposed method.

控制棒驱动机构（CRDM）是核反应堆的关键设备，预测其剩余使用寿命（RUL）对于高效维护和确保核电站安全可靠运行非常重要。本文提出了一种新颖的 CRDM RUL 预测框架，即基于动态激活函数和注意力机制的动态时空卷积网络（DTCN）。首先，将时态卷积网络（TCN）作为预测模型的骨干，提取输入数据的时态依赖性。然后，将动态激活函数 DReLU 集成到 TCN 中，该函数可以动态激活特征并捕捉变量退化信息。然后，引入关注机制，提高网络提取的重要高级特征对 RUL 预测的影响，从而提高网络特征提取的效率。最后，DTCN 通过对提取的特征进行非线性映射，输出预测的 RUL。建立了 CRDM 加速寿命测试平台，并利用收集到的 CRDM 全寿命振动数据集进行了一系列实验。结果证明了所提方法的性能和优势。

{"title":"Remaining useful life prediction of nuclear reactor control rod drive mechanism based on dynamic temporal convolutional network","authors":"","doi":"10.1016/j.ress.2024.110580","DOIUrl":"10.1016/j.ress.2024.110580","url":null,"abstract":"<div><div>The control rod drive mechanism (CRDM) is a critical equipment of the nuclear reactor, and the prediction of its remaining useful life (RUL) is important for the efficient maintenance and ensuring the safe, reliable operation of nuclear power plants. In this paper, a novel framework for the RUL prediction of CRDM is proposed, which is a dynamic temporal convolution network (DTCN) based on dynamic activation function and attention mechanism. Firstly, the temporal convolution network (TCN) is used as the backbone of the prediction model, to extract the temporal dependence of the input data. Next, the dynamic activation function DReLU is integrated into the TCN, which can dynamically activate features and capture variable degradation information. Then, introducing the attention mechanism improves the influence of important high-level features extracted by the network on RUL prediction, thereby improving the efficiency of feature extraction in the network. Finally, the DTCN outputs the predicted RUL by performing non-linear mapping on the extracted features. The CRDM accelerated life test platform is established and a series of experiments are conducted using the collected CRDM full-life vibration dataset. The results demonstrated the performance and advantages of the proposed method.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":null,"pages":null},"PeriodicalIF":9.4,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142442859","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

Efficient risk-based inspection framework: Balancing safety and budgetary constraints 基于风险的高效检查框架：平衡安全与预算限制

IF 9.4 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Reliability Engineering & System Safety

Pub Date : 2024-10-10 DOI: 10.1016/j.ress.2024.110519

Efficient equipment maintenance is paramount across various industries to mitigate energy wastage and avert potential disasters such as hazardous emissions, fires, and explosions. Within this context, the adoption of risk-based inspection strategies has emerged as a crucial method for assessing equipment integrity. This study integrates the principles of Risk-Based Inspection (RBI) with a novel two-objective mathematical model, resulting in a comprehensive framework for equipment inspection programs. The primary aim of this framework is to reduce overall risk exposure while optimizing inspection expenditures. Unlike conventional approaches, this methodology eliminates the necessity to define threshold risk levels. By integrating inspection costs into the model, the assessment of Failure Consequences, and thereby, the decision-making process has been streamlined. This innovative algorithm effectively balances the reduction of failure likelihood with the minimization of inspection costs, enhancing decision-making capabilities. Importantly, this approach offers significant protection against energy wastage and the occurrence of leaks through robust risk management strategies. The algorithm employs specialized operators to expedite the discovery of optimal solutions. Empirical validation through a case study conducted at a Petrochemical Plant highlights the practicality and effectiveness of the proposed framework.

在各行各业中，高效的设备维护对于减少能源浪费和避免危险排放、火灾和爆炸等潜在灾难至关重要。在此背景下，采用基于风险的检测策略已成为评估设备完整性的重要方法。本研究将基于风险的检查（RBI）原则与一个新颖的双目标数学模型相结合，为设备检查项目提供了一个综合框架。该框架的主要目的是降低整体风险，同时优化检查支出。与传统方法不同，该方法无需定义阈值风险水平。通过将检测成本纳入模型，故障后果的评估以及决策过程都得到了简化。这种创新算法有效地平衡了降低故障可能性与检查成本最小化之间的关系，从而提高了决策能力。重要的是，这种方法通过强有力的风险管理策略，为防止能源浪费和发生泄漏提供了重要保护。该算法采用了专门的运算器，以加快发现最佳解决方案。通过在一家石油化工厂进行的案例研究进行的经验验证，凸显了所提框架的实用性和有效性。

{"title":"Efficient risk-based inspection framework: Balancing safety and budgetary constraints","authors":"","doi":"10.1016/j.ress.2024.110519","DOIUrl":"10.1016/j.ress.2024.110519","url":null,"abstract":"<div><div>Efficient equipment maintenance is paramount across various industries to mitigate energy wastage and avert potential disasters such as hazardous emissions, fires, and explosions. Within this context, the adoption of risk-based inspection strategies has emerged as a crucial method for assessing equipment integrity. This study integrates the principles of Risk-Based Inspection (RBI) with a novel two-objective mathematical model, resulting in a comprehensive framework for equipment inspection programs. The primary aim of this framework is to reduce overall risk exposure while optimizing inspection expenditures. Unlike conventional approaches, this methodology eliminates the necessity to define threshold risk levels. By integrating inspection costs into the model, the assessment of Failure Consequences, and thereby, the decision-making process has been streamlined. This innovative algorithm effectively balances the reduction of failure likelihood with the minimization of inspection costs, enhancing decision-making capabilities. Importantly, this approach offers significant protection against energy wastage and the occurrence of leaks through robust risk management strategies. The algorithm employs specialized operators to expedite the discovery of optimal solutions. Empirical validation through a case study conducted at a Petrochemical Plant highlights the practicality and effectiveness of the proposed framework.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":null,"pages":null},"PeriodicalIF":9.4,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142530317","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

Failure time analysis for compound degradation procedures involving linear path and negative jumps 涉及线性路径和负跳跃的复合降解程序的故障时间分析

IF 9.4 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Reliability Engineering & System Safety

Pub Date : 2024-10-10 DOI: 10.1016/j.ress.2024.110566

Failure time analysis for compound degradation process involving abrupt jumps has attracted significant attention in recent years. Particularly, considering the situation of recovery or maintenance, which exists extensively in project reality, degradation process with negative jumps has been increasingly highlighted. However, due to the randomness and the complicated nonmonotonicity aroused by negative jumps, analyzing its first hitting time distribution is a great challenge at current stage. In this paper, aiming at the failure time analysis itself, the concept of invalid epoch is proposed firstly based on the characteristics of this kind of degradation process. Then, a novel analytical solution of lifetime distribution under the concept of the first hitting time is derived in the form of Laplace–Stieltjes transform, and it is further extended to some typical cases. To demonstrate the feasibility and the effectiveness, a series of verifications are carried out comprehensively. Results show that the solution is well-performed under different parameter settings. Finally, the proposed method is applied to a real application of draught fans to illustrate the validity.

近年来，涉及突然跳变的复合退化过程的故障时间分析引起了人们的极大关注。特别是考虑到工程实际中广泛存在的恢复或维护情况，具有负跳跃的退化过程日益受到重视。然而，由于负跳跃的随机性和复杂的非单调性，分析其首次命中时间分布是现阶段的一大难题。本文针对失效时间分析本身，首先根据这种退化过程的特点，提出了失效历时的概念。然后，以拉普拉斯-斯蒂尔杰斯变换的形式推导出了首击时间概念下寿命分布的新型解析解，并将其进一步推广到一些典型案例中。为了证明其可行性和有效性，我们进行了一系列综合验证。结果表明，在不同的参数设置下，求解效果良好。最后，将提出的方法应用于引风机的实际应用中，以说明其有效性。

{"title":"Failure time analysis for compound degradation procedures involving linear path and negative jumps","authors":"","doi":"10.1016/j.ress.2024.110566","DOIUrl":"10.1016/j.ress.2024.110566","url":null,"abstract":"<div><div>Failure time analysis for compound degradation process involving abrupt jumps has attracted significant attention in recent years. Particularly, considering the situation of recovery or maintenance, which exists extensively in project reality, degradation process with negative jumps has been increasingly highlighted. However, due to the randomness and the complicated nonmonotonicity aroused by negative jumps, analyzing its first hitting time distribution is a great challenge at current stage. In this paper, aiming at the failure time analysis itself, the concept of invalid epoch is proposed firstly based on the characteristics of this kind of degradation process. Then, a novel analytical solution of lifetime distribution under the concept of the first hitting time is derived in the form of Laplace–Stieltjes transform, and it is further extended to some typical cases. To demonstrate the feasibility and the effectiveness, a series of verifications are carried out comprehensively. Results show that the solution is well-performed under different parameter settings. Finally, the proposed method is applied to a real application of draught fans to illustrate the validity.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":null,"pages":null},"PeriodicalIF":9.4,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142530315","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

Fault Impulse Inference and Cyclostationary Approximation: A feature-interpretable intelligent fault detection method for few-shot unsupervised domain adaptation 故障脉冲推理和循环近似：一种可解释特征的智能故障检测方法，适用于少量无监督域适应

IF 9.4 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Reliability Engineering & System Safety

Pub Date : 2024-10-10 DOI: 10.1016/j.ress.2024.110568

With the advancement of intelligent detection for rotating machinery, numerous domain adaptation methods have been devised to transfer detection knowledge from one source domain working condition to another target domain working condition, involving extensive transfer scenarios including labeled, few-shot labeled, and unlabeled target conditions. Yet, learning from sparsely labeled signals in the source domain working condition and transferring to unlabeled target conditions, termed few-shot unsupervised domain adaptation (FUDA), is closer to reality but almost unexplored. Diverging from the intuition of combining existing transfer and few-shot learning technologies, this paper pioneers a novel single learning principle focusing on the cyclostationary mechanism (CT) of fault signals. In its implementation, named cyclically enhanced cyclostationary variational autoencoder (CCTVAE), the CT principle motivates the encoder to infer domain-shared representations with fault impulses, and the decoder approximates the cyclostationary structure containing the clear fault and working condition information. Then, auxiliary samples for few-shot expansion are generated by adjusting cyclic parameters of the posterior distribution of representations. Experimentally, CCTVAE achieves commendable results on simulated and real fault datasets. Even for compound faults, domain-shared representations and generated auxiliary signals manifest interpretable fault-indicating spectral lines in the frequency domain, underscoring method reliability.

随着旋转机械智能检测技术的发展，人们设计了许多域自适应方法，将检测知识从一个源域工作条件转移到另一个目标域工作条件，涉及广泛的转移场景，包括有标记、少量标记和无标记目标条件。然而，从源域工作条件下的稀疏标记信号中学习并转移到无标记目标条件下的检测知识，被称为少镜头无监督域自适应（FUDA），这种方法更接近现实，但几乎尚未被探索。本文不同于将现有的转移学习和少量学习技术相结合的直觉，而是开创了一种新的单一学习原理，重点关注故障信号的循环静态机制（CT）。在被命名为循环增强循环变异自动编码器（CCTVAE）的实现过程中，CT 原理促使编码器推断出与故障脉冲相关的领域共享表征，解码器近似包含明确故障和工作状态信息的循环结构。然后，通过调整表征后验分布的循环参数，生成用于少量扩展的辅助样本。在实验中，CCTVAE 在模拟和真实故障数据集上取得了值得称赞的结果。即使是复合故障，域共享表示和生成的辅助信号也能在频域上显示可解释的故障指示频谱线，从而突出了该方法的可靠性。

{"title":"Fault Impulse Inference and Cyclostationary Approximation: A feature-interpretable intelligent fault detection method for few-shot unsupervised domain adaptation","authors":"","doi":"10.1016/j.ress.2024.110568","DOIUrl":"10.1016/j.ress.2024.110568","url":null,"abstract":"<div><div>With the advancement of intelligent detection for rotating machinery, numerous domain adaptation methods have been devised to transfer detection knowledge from one source domain working condition to another target domain working condition, involving extensive transfer scenarios including labeled, few-shot labeled, and unlabeled target conditions. Yet, learning from sparsely labeled signals in the source domain working condition and transferring to unlabeled target conditions, termed few-shot unsupervised domain adaptation (FUDA), is closer to reality but almost unexplored. Diverging from the intuition of combining existing transfer and few-shot learning technologies, this paper pioneers a novel single learning principle focusing on the cyclostationary mechanism (CT) of fault signals. In its implementation, named cyclically enhanced cyclostationary variational autoencoder (CCTVAE), the CT principle motivates the encoder to infer domain-shared representations with fault impulses, and the decoder approximates the cyclostationary structure containing the clear fault and working condition information. Then, auxiliary samples for few-shot expansion are generated by adjusting cyclic parameters of the posterior distribution of representations. Experimentally, CCTVAE achieves commendable results on simulated and real fault datasets. Even for compound faults, domain-shared representations and generated auxiliary signals manifest interpretable fault-indicating spectral lines in the frequency domain, underscoring method reliability.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":null,"pages":null},"PeriodicalIF":9.4,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142438441","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 hybrid dual-frequency-informed spider net for RUL prognosis with adaptive IDP detection and outlier correction 利用自适应 IDP 检测和离群值校正进行 RUL 预报的混合双频信息蜘蛛网

IF 9.4 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Reliability Engineering & System Safety

Pub Date : 2024-10-10 DOI: 10.1016/j.ress.2024.110518

The present study proposes a novel framework to estimate the Remaining Useful Life (RUL) of bearings operating under variable operating conditions, addressing two critical challenges: early detection of the Initial Degradation Point (IDP) in bearings and correction of outlier values. A unique Spider cell prediction unit with dual-frequency correction is proposed. Firstly, a generalized adaptive method is introduced for early IDP detection, leveraging the slope and intercept, along with coupled t-tests to formulate a "sum of slopes" index for detecting the IDP. Secondly, a degradation feature extraction method is introduced, which utilizes synchronous pseudo speed in combination with sliding window averaging. Outlier correction for degradation feature indicators is achieved using constructed boundary conditions. Thirdly, a variational mode decomposition layer is proposed to decompose the input sample into different mode function components. Finally, a novel RUL prediction correction module, where two types of frequency domain feature extractors with trainable parameters are designed to adjust the prediction results of the Spider net by capturing both global trend changes and local details.

本研究提出了一个新框架，用于估算在多变工作条件下运行的轴承的剩余使用寿命（RUL），解决了两个关键难题：轴承初始退化点（IDP）的早期检测和离群值的校正。本文提出了一种具有双频校正功能的独特 Spider 单元预测单元。首先，引入了一种用于早期 IDP 检测的通用自适应方法，利用斜率和截距以及耦合 t 检验来制定用于检测 IDP 的 "斜率之和 "指标。其次，引入了退化特征提取方法，该方法利用同步伪速度与滑动窗口平均相结合。利用构造边界条件实现退化特征指标的离群校正。第三，提出了变分模式分解层，将输入样本分解为不同的模式函数分量。最后，设计了一个新颖的 RUL 预测修正模块，该模块设计了两种具有可训练参数的频域特征提取器，通过捕捉全局趋势变化和局部细节来调整 Spider 网的预测结果。

{"title":"A hybrid dual-frequency-informed spider net for RUL prognosis with adaptive IDP detection and outlier correction","authors":"","doi":"10.1016/j.ress.2024.110518","DOIUrl":"10.1016/j.ress.2024.110518","url":null,"abstract":"<div><div>The present study proposes a novel framework to estimate the Remaining Useful Life (RUL) of bearings operating under variable operating conditions, addressing two critical challenges: early detection of the Initial Degradation Point (IDP) in bearings and correction of outlier values. A unique Spider cell prediction unit with dual-frequency correction is proposed. Firstly, a generalized adaptive method is introduced for early IDP detection, leveraging the slope and intercept, along with coupled <em>t</em>-tests to formulate a \"sum of slopes\" index for detecting the IDP. Secondly, a degradation feature extraction method is introduced, which utilizes synchronous pseudo speed in combination with sliding window averaging. Outlier correction for degradation feature indicators is achieved using constructed boundary conditions. Thirdly, a variational mode decomposition layer is proposed to decompose the input sample into different mode function components. Finally, a novel RUL prediction correction module, where two types of frequency domain feature extractors with trainable parameters are designed to adjust the prediction results of the Spider net by capturing both global trend changes and local details.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":null,"pages":null},"PeriodicalIF":9.4,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142420992","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

PLIC-FSR-SYS: System reliability analysis based on parallel learning of influential components with filtered sample region PLIC-FSR-SYS：基于带过滤样本区域的影响成分并行学习的系统可靠性分析

IF 9.4 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Reliability Engineering & System Safety

Pub Date : 2024-10-10 DOI: 10.1016/j.ress.2024.110583

In practical engineering, system reliability analysis is highly concerned since many structures or products have multiple failure modes. Accordingly, this paper develops an innovative method for system reliability analysis by parallel learning of influential component limit-state functions with filtered sample region (PLIC-FSR-SYS) based on Kriging modeling. Different from the traditional adaptive learning methods that train only one component in each iteration when constructing the surrogate of the composite limit-state function, a new strategy is explored to adaptively identify several important components in one iteration so as to train them simultaneously. In the meanwhile, a filtering formula is explored to determine the fatal region so that the unimportant samples can be removed to further accelerate the training process. Based on the join forces of parallel learning of influential components and avoiding the training at unimportant samples, PLIC-FSR-SYS can achieve a fairly efficient system reliability analysis with multiple failure modes. Finally, four different case studies, including an engineering application to the ultra-voltage on-load tap-changer, are conducted to prove the effectiveness of the proposed method. The results indicate that compared to traditional adaptive learning methods, the proposed method makes a significant efficiency improvement for system reliability analysis with multiple failure modes.

在实际工程中，由于许多结构或产品具有多种失效模式，因此系统可靠性分析备受关注。因此，本文在克里金建模的基础上，开发了一种创新的系统可靠性分析方法，即基于滤波采样区域的影响元件极限状态函数并行学习法（PLIC-FSR-SYS）。不同于传统的自适应学习方法在构建复合极限状态函数代理时每次迭代只训练一个分量，本文探索了一种新策略，即在一次迭代中自适应地识别多个重要分量，从而同时训练它们。同时，探索一种过滤公式来确定致命区域，从而去除不重要的样本，进一步加快训练过程。基于并行学习有影响的组件和避免训练不重要的样本这两种方法的联合作用，PLIC-FSR-SYS 可以实现相当高效的多失效模式系统可靠性分析。最后，为了证明所提方法的有效性，我们进行了四项不同的案例研究，其中包括对超高压有载分接开关的工程应用。结果表明，与传统的自适应学习方法相比，所提出的方法能显著提高多失效模式系统可靠性分析的效率。

{"title":"PLIC-FSR-SYS: System reliability analysis based on parallel learning of influential components with filtered sample region","authors":"","doi":"10.1016/j.ress.2024.110583","DOIUrl":"10.1016/j.ress.2024.110583","url":null,"abstract":"<div><div>In practical engineering, system reliability analysis is highly concerned since many structures or products have multiple failure modes. Accordingly, this paper develops an innovative method for system reliability analysis by parallel learning of influential component limit-state functions with filtered sample region (PLIC-FSR-SYS) based on Kriging modeling. Different from the traditional adaptive learning methods that train only one component in each iteration when constructing the surrogate of the composite limit-state function, a new strategy is explored to adaptively identify several important components in one iteration so as to train them simultaneously. In the meanwhile, a filtering formula is explored to determine the fatal region so that the unimportant samples can be removed to further accelerate the training process. Based on the join forces of parallel learning of influential components and avoiding the training at unimportant samples, PLIC-FSR-SYS can achieve a fairly efficient system reliability analysis with multiple failure modes. Finally, four different case studies, including an engineering application to the ultra-voltage on-load tap-changer, are conducted to prove the effectiveness of the proposed method. The results indicate that compared to traditional adaptive learning methods, the proposed method makes a significant efficiency improvement for system reliability analysis with multiple failure modes.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":null,"pages":null},"PeriodicalIF":9.4,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142433323","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

Uncertainty-based multi-objective optimization in twin tunnel design considering fluid-solid coupling 考虑流固耦合的双隧道设计中基于不确定性的多目标优化

IF 9.4 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Reliability Engineering & System Safety

Pub Date : 2024-10-10 DOI: 10.1016/j.ress.2024.110575

This paper presents a multi-objective optimization framework based on uncertainty analysis, focusing on fluid–structure interaction in twin tunnel design. High-quality datasets are generated using three-dimensional fluid–structure interaction theory. Long Short-Term Memory-Attention (LSTM-Attention) models are used to simulate internal forces within the tunnel and ground settlement, improving prediction accuracy. The Snow Ablation Optimizer (SAO) adjusts the hyperparameters of the LSTM-Attention model. The SHapley Additive exPlanations (SHAP) framework is introduced to enhance the model’s transparency and interpretability, aiding in understanding the model’s decision-making process. The hybrid Non-dominated Sorting Genetic Algorithm II (NSGA-II) combined with Particle Swarm Optimization (PSO) is employed for multi-objective optimization. Monte Carlo simulation is used to estimate probability constraints, ensuring that the optimization process yields stable and reliable solutions. A case study analyzes the optimization results under different tunnel radii and uncertainty conditions in detail, validating the method’s effectiveness. The study shows that considering uncertainty significantly enhances the accuracy and stability of the optimization results for internal forces and ground settlement. Additionally, under different tunnel radii and uncertainty conditions, the distribution of optimal solutions is more concentrated. This method provides a novel solution for multi-objective optimization in complex engineering problems and offers theoretical and practical guidance for engineering decision-making and optimization.

本文提出了一种基于不确定性分析的多目标优化框架，重点关注双洞隧道设计中的流固耦合问题。利用三维流固耦合理论生成高质量数据集。长短期记忆-注意力（LSTM-Attention）模型用于模拟隧道内力和地面沉降，从而提高预测精度。雪消融优化器（SAO）可调整 LSTM-Attention 模型的超参数。引入了 SHapley Additive exPlanations（SHAP）框架，以提高模型的透明度和可解释性，帮助理解模型的决策过程。混合非支配排序遗传算法 II（NSGA-II）与粒子群优化（PSO）相结合，用于多目标优化。蒙特卡罗模拟用于估计概率约束，确保优化过程产生稳定可靠的解决方案。案例研究详细分析了不同隧道半径和不确定性条件下的优化结果，验证了该方法的有效性。研究表明，考虑不确定性能显著提高内力和地面沉降优化结果的准确性和稳定性。此外，在不同的隧道半径和不确定性条件下，最优解的分布更加集中。该方法为复杂工程问题的多目标优化提供了一种新的解决方案，为工程决策和优化提供了理论和实践指导。

{"title":"Uncertainty-based multi-objective optimization in twin tunnel design considering fluid-solid coupling","authors":"","doi":"10.1016/j.ress.2024.110575","DOIUrl":"10.1016/j.ress.2024.110575","url":null,"abstract":"<div><div>This paper presents a multi-objective optimization framework based on uncertainty analysis, focusing on fluid–structure interaction in twin tunnel design. High-quality datasets are generated using three-dimensional fluid–structure interaction theory. Long Short-Term Memory-Attention (LSTM-Attention) models are used to simulate internal forces within the tunnel and ground settlement, improving prediction accuracy. The Snow Ablation Optimizer (SAO) adjusts the hyperparameters of the LSTM-Attention model. The SHapley Additive exPlanations (SHAP) framework is introduced to enhance the model’s transparency and interpretability, aiding in understanding the model’s decision-making process. The hybrid Non-dominated Sorting Genetic Algorithm II (NSGA-II) combined with Particle Swarm Optimization (PSO) is employed for multi-objective optimization. Monte Carlo simulation is used to estimate probability constraints, ensuring that the optimization process yields stable and reliable solutions. A case study analyzes the optimization results under different tunnel radii and uncertainty conditions in detail, validating the method’s effectiveness. The study shows that considering uncertainty significantly enhances the accuracy and stability of the optimization results for internal forces and ground settlement. Additionally, under different tunnel radii and uncertainty conditions, the distribution of optimal solutions is more concentrated. This method provides a novel solution for multi-objective optimization in complex engineering problems and offers theoretical and practical guidance for engineering decision-making and optimization.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":null,"pages":null},"PeriodicalIF":9.4,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142433324","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

Generalized zero-sample industrial fault diagnosis with domain bias 带域偏差的广义零样本工业故障诊断

IF 9.4 1区工程技术 Q1 ENGINEERING, INDUSTRIAL

Reliability Engineering & System Safety

Pub Date : 2024-10-10 DOI: 10.1016/j.ress.2024.110571

Generalized zero-sample fault diagnosis (GZSFD) is a challenging task involving the diagnosis of all samples from both previously seen and unseen faults. However, the scarcity of unseen samples for training causes that existing methods are hindered by domain bias, where unseen faults are more likely to be misclassified as seen faults. In this article, an efficacious solution is proposed by constructing an unseen fault detector for test samples in GZSFD with domain bias, which utilizes the detected unseen-sample knowledge to enhance the diagnosis performance. Specifically, a ResNet-based one-dimensional convolutional neural network is designed for high-quality feature extraction. Also, a Kullback–Leibler divergence-based distribution threshold detector is constructed for the identification of test samples. Afterwards, test samples are detected and distinguished into seen or unseen classes. In detected unseen classes, a zero-sample fault diagnosis (ZSFD) problem is undertaken, while in detected seen classes, a sub-GZSFD problem is addressed. For ZSFD tasks, to leverage the unseen samples in the test set, a clustering-based scheme without a predefined cluster number is used for the detected unseen fault. For sub-GZSFD tasks, combined with classification results in the ZSFD task, two embedding strategies are proposed to further mitigate the domain bias. They learn a shared weight and the optimal weights of semantic attributes from the feature space to the semantic embedding space, respectively. Using the shared fine-grained semantic attribute descriptions as auxiliary information, the final fault category can be determined. Experimental results showcase that the proposed strategies effectively alleviate the domain bias in GZSFD tasks.

广义零样本故障诊断（GZSFD）是一项极具挑战性的任务，它涉及对所有样本进行诊断，这些样本既包括以前出现过的故障，也包括未出现过的故障。然而，用于训练的未见样本的稀缺性导致现有方法受到领域偏差的阻碍，未见故障更有可能被误判为已见故障。本文提出了一种有效的解决方案，即为具有领域偏差的 GZSFD 中的测试样本构建未见故障检测器，利用检测到的未见样本知识提高诊断性能。具体来说，设计了一个基于 ResNet 的一维卷积神经网络，用于高质量特征提取。此外，还构建了基于库尔贝-莱布勒发散的分布阈值检测器，用于识别测试样本。然后，检测测试样本并将其区分为可见类和未见类。在检测到的未见类中，要解决零样本故障诊断（ZSFD）问题，而在检测到的可见类中，要解决子 ZSFD 问题。在零样本故障诊断任务中，为了充分利用测试集中的未见样本，对检测到的未见故障采用了基于聚类的方案，但没有预定义的聚类数量。对于子 ZSFD 任务，结合 ZSFD 任务中的分类结果，提出了两种嵌入策略，以进一步减轻领域偏差。它们分别从特征空间到语义嵌入空间学习语义属性的共享权重和最优权重。利用共享的细粒度语义属性描述作为辅助信息，可以确定最终的故障类别。实验结果表明，所提出的策略能有效缓解 GZSFD 任务中的领域偏差。

{"title":"Generalized zero-sample industrial fault diagnosis with domain bias","authors":"","doi":"10.1016/j.ress.2024.110571","DOIUrl":"10.1016/j.ress.2024.110571","url":null,"abstract":"<div><div>Generalized zero-sample fault diagnosis (GZSFD) is a challenging task involving the diagnosis of all samples from both previously seen and unseen faults. However, the scarcity of unseen samples for training causes that existing methods are hindered by domain bias, where unseen faults are more likely to be misclassified as seen faults. In this article, an efficacious solution is proposed by constructing an unseen fault detector for test samples in GZSFD with domain bias, which utilizes the detected unseen-sample knowledge to enhance the diagnosis performance. Specifically, a ResNet-based one-dimensional convolutional neural network is designed for high-quality feature extraction. Also, a Kullback–Leibler divergence-based distribution threshold detector is constructed for the identification of test samples. Afterwards, test samples are detected and distinguished into seen or unseen classes. In detected unseen classes, a zero-sample fault diagnosis (ZSFD) problem is undertaken, while in detected seen classes, a sub-GZSFD problem is addressed. For ZSFD tasks, to leverage the unseen samples in the test set, a clustering-based scheme without a predefined cluster number is used for the detected unseen fault. For sub-GZSFD tasks, combined with classification results in the ZSFD task, two embedding strategies are proposed to further mitigate the domain bias. They learn a shared weight and the optimal weights of semantic attributes from the feature space to the semantic embedding space, respectively. Using the shared fine-grained semantic attribute descriptions as auxiliary information, the final fault category can be determined. Experimental results showcase that the proposed strategies effectively alleviate the domain bias in GZSFD tasks.</div></div>","PeriodicalId":54500,"journal":{"name":"Reliability Engineering & System Safety","volume":null,"pages":null},"PeriodicalIF":9.4,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142530320","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