Global navigation satellite systems (GNSS) often suffer from service interruptions or multipath errors in urban canyon environments, giving rise to reduced navigation accuracy. Therefore, it is necessary to develop effective fault-tolerant navigation systems to ensure a high-level accuracy despite GNSS failures. In this article, we present a novel fault detection framework based on the extended Kalman filter to address the problem of untimely fault detection and inaccurate positioning when GNSS fails. Specifically, we introduce the statistical process control technique of control charts to address the issue of slow-varying fault detection by constructing kernel multivariate exponentially weighted moving-average control charts instead of the conventional chi-square test. Simultaneously, we establish a corresponding criterion using EWMA-related statistics to mitigate the negative impact of uncertain noise and abnormal innovation, thereby ensuring the positioning accuracy of the navigation system. Finally, we validate the effectiveness and superiority of the proposed method through simulations and vehicle field data, demonstrating its ability to detect anomalies promptly and enhance the navigation and positioning accuracy while mitigating the adverse effects of GNSS lapse.
{"title":"A Novel Fault Detection Framework-Based Extend Kalman Filter for Fault-Tolerant Navigation System","authors":"Zhiyuan Jiao;Xiyuan Chen;Ning Gao","doi":"10.1109/TR.2024.3405026","DOIUrl":"10.1109/TR.2024.3405026","url":null,"abstract":"Global navigation satellite systems (GNSS) often suffer from service interruptions or multipath errors in urban canyon environments, giving rise to reduced navigation accuracy. Therefore, it is necessary to develop effective fault-tolerant navigation systems to ensure a high-level accuracy despite GNSS failures. In this article, we present a novel fault detection framework based on the extended Kalman filter to address the problem of untimely fault detection and inaccurate positioning when GNSS fails. Specifically, we introduce the statistical process control technique of control charts to address the issue of slow-varying fault detection by constructing kernel multivariate exponentially weighted moving-average control charts instead of the conventional chi-square test. Simultaneously, we establish a corresponding criterion using EWMA-related statistics to mitigate the negative impact of uncertain noise and abnormal innovation, thereby ensuring the positioning accuracy of the navigation system. Finally, we validate the effectiveness and superiority of the proposed method through simulations and vehicle field data, demonstrating its ability to detect anomalies promptly and enhance the navigation and positioning accuracy while mitigating the adverse effects of GNSS lapse.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 1","pages":"2056-2068"},"PeriodicalIF":5.0,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141942538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jingyu Zhang;Jacky Wai Keung;Yan Xiao;Yihan Liao;Yishu Li;Xiaoxue Ma
Adversarial attacks play a pivotal role in testing and improving the reliability of deep learning (DL) systems. Existing literature has demonstrated that subtle perturbations to the input can elicit erroneous outcomes, thereby substantially compromising the security of DL systems. This has emerged as a critical concern in the development of DL-based safety–critical systems like autonomous driving systems (ADSs). The focus of existing adversarial attack methods on end-to-end (E2E) ADSs has predominantly centered on misbehaviors of steering angle, which overlooks speed-related controls or imperceptible perturbations. To address these challenges, we introduce UniAda–a multiobjective white-box attack technique with a core function that revolves around crafting an image-agnostic adversarial perturbation capable of simultaneously influencing both steering and speed controls. UniAda capitalizes on an intricately designed multiobjective optimization function with the adaptive weighting scheme (AWS), enabling the concurrent optimization of diverse objectives. Validated with both simulated and real-world driving data, UniAda outperforms five benchmarks across two metrics, inducing steering and speed deviations from 3.54 $^{circ }$ to 29 $^{circ }$ and 11 to 22 km/h on average. This systematic approach establishes UniAda as a proven technique for adversarial attacks on modern DL-based E2E ADSs.
{"title":"UniAda: Universal Adaptive Multiobjective Adversarial Attack for End-to-End Autonomous Driving Systems","authors":"Jingyu Zhang;Jacky Wai Keung;Yan Xiao;Yihan Liao;Yishu Li;Xiaoxue Ma","doi":"10.1109/TR.2024.3394894","DOIUrl":"10.1109/TR.2024.3394894","url":null,"abstract":"Adversarial attacks play a pivotal role in testing and improving the reliability of deep learning (DL) systems. Existing literature has demonstrated that subtle perturbations to the input can elicit erroneous outcomes, thereby substantially compromising the security of DL systems. This has emerged as a critical concern in the development of DL-based safety–critical systems like autonomous driving systems (ADSs). The focus of existing adversarial attack methods on end-to-end (E2E) ADSs has predominantly centered on misbehaviors of steering angle, which overlooks speed-related controls or imperceptible perturbations. To address these challenges, we introduce UniAda–a multiobjective white-box attack technique with a core function that revolves around crafting an image-agnostic adversarial perturbation capable of simultaneously influencing both steering and speed controls. UniAda capitalizes on an intricately designed multiobjective optimization function with the adaptive weighting scheme (AWS), enabling the concurrent optimization of diverse objectives. Validated with both simulated and real-world driving data, UniAda outperforms five benchmarks across two metrics, inducing steering and speed deviations from 3.54\u0000<inline-formula><tex-math>$^{circ }$</tex-math></inline-formula>\u0000 to 29\u0000<inline-formula><tex-math>$^{circ }$</tex-math></inline-formula>\u0000 and 11 to 22 km/h on average. This systematic approach establishes UniAda as a proven technique for adversarial attacks on modern DL-based E2E ADSs.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"73 4","pages":"1892-1906"},"PeriodicalIF":5.0,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141942569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Transfer learning (TL) is a powerful approach that enhances the generalizability of cross-domain fault diagnosis. However, the challenge of acquiring high-quality mechanical fault signals limits its application. This article introduces the extreme class imbalance problem in the cross-domain diagnosis, restricting the label space of the target domain while relaxing the restrictions of unsupervised learning. The study proposes a novel generative TL method called fast sparse neural style, which employs sparse representation to capture the domain-invariant fault features as well as the Gram matrix to measure the domain-specific features. Fault features and domain features are proven to be separable in mechanical signals and are fused in the data generation process. Compared to other methods through various cross-domain diagnostic tasks on a piston aero-engine, the proposed method has obvious advantages in tasks with substantial inter-domain differences, demonstrating the potential and research value of generative TL.
{"title":"A Generative Transfer Learning Method for Extreme Class Imbalance Problem and Applied to Piston Aero-Engine Fault Cross-Domain Diagnosis","authors":"Pengfei Shen;Fengrong Bi;Xiaoyang Bi;Xiao Yang;Daijie Tang;Mingzhi Guo","doi":"10.1109/TR.2024.3403660","DOIUrl":"10.1109/TR.2024.3403660","url":null,"abstract":"Transfer learning (TL) is a powerful approach that enhances the generalizability of cross-domain fault diagnosis. However, the challenge of acquiring high-quality mechanical fault signals limits its application. This article introduces the extreme class imbalance problem in the cross-domain diagnosis, restricting the label space of the target domain while relaxing the restrictions of unsupervised learning. The study proposes a novel generative TL method called fast sparse neural style, which employs sparse representation to capture the domain-invariant fault features as well as the Gram matrix to measure the domain-specific features. Fault features and domain features are proven to be separable in mechanical signals and are fused in the data generation process. Compared to other methods through various cross-domain diagnostic tasks on a piston aero-engine, the proposed method has obvious advantages in tasks with substantial inter-domain differences, demonstrating the potential and research value of generative TL.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 1","pages":"2434-2447"},"PeriodicalIF":5.0,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141942539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In today's digital environment, nearly every industry faces challenges concerning reliability, security, and trust. Ensuring that systems persist in operation despite hacker threats and that enterprises can effectively safeguard their assets are paramount concerns.
{"title":"Editorial Ensuring Reliability, Security, and Trust for Enterprises","authors":"Winston Shieh","doi":"10.1109/TR.2024.3398409","DOIUrl":"https://doi.org/10.1109/TR.2024.3398409","url":null,"abstract":"In today's digital environment, nearly every industry faces challenges concerning reliability, security, and trust. Ensuring that systems persist in operation despite hacker threats and that enterprises can effectively safeguard their assets are paramount concerns.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"73 2","pages":"805-807"},"PeriodicalIF":5.9,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10547162","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141245078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As a key water quality parameter in the wastewater treatment process (WWTP), the accurate measurement of total phosphorus (TP) would effectively prevent the effluent water from eutrophication. Although soft measurement models can successfully predict effluent TP, the model prediction is unreliable because outliers will inevitably exist in actual WWTP due to a variety of disturbances. To solve this problem, a novel robust small-world feedforward neural network (RSWFNN) is proposed to improve the robustness of effluent TP prediction. First, the robust Spearman rank correlation analysis is used to determine auxiliary variables intrinsically correlated with the effluent TP. Second, inspired by the fault tolerance of the human brain from its small world property, the small-worldness is introduced to obtain a robust network architecture. Third, the robust learning algorithm using the loss function of regularized M-estimation is proposed to suppress the responses of outliers to improve the robustness of the model. Finally, the corresponding two hyperparameters are determined by an adaptive adjustment strategy, thus ensuring the effectiveness of suppressing outliers. Our experimental results have shown that RSWFNN has stronger robustness and better prediction performance to predict effluent TP than other modeling methods, and the superiority of robustness becomes more obvious with the increase of outlier proportion.
{"title":"Robust Neural Network Modeling With Small-Worldness for Effluent Total Phosphorus Prediction in Wastewater Treatment Process","authors":"Wenjing Li;Chong Ding;Junfei Qiao","doi":"10.1109/TR.2024.3399735","DOIUrl":"10.1109/TR.2024.3399735","url":null,"abstract":"As a key water quality parameter in the wastewater treatment process (WWTP), the accurate measurement of total phosphorus (TP) would effectively prevent the effluent water from eutrophication. Although soft measurement models can successfully predict effluent TP, the model prediction is unreliable because outliers will inevitably exist in actual WWTP due to a variety of disturbances. To solve this problem, a novel robust small-world feedforward neural network (RSWFNN) is proposed to improve the robustness of effluent TP prediction. First, the robust Spearman rank correlation analysis is used to determine auxiliary variables intrinsically correlated with the effluent TP. Second, inspired by the fault tolerance of the human brain from its small world property, the small-worldness is introduced to obtain a robust network architecture. Third, the robust learning algorithm using the loss function of regularized M-estimation is proposed to suppress the responses of outliers to improve the robustness of the model. Finally, the corresponding two hyperparameters are determined by an adaptive adjustment strategy, thus ensuring the effectiveness of suppressing outliers. Our experimental results have shown that RSWFNN has stronger robustness and better prediction performance to predict effluent TP than other modeling methods, and the superiority of robustness becomes more obvious with the increase of outlier proportion.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 1","pages":"2473-2486"},"PeriodicalIF":5.0,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141942540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"IEEE Reliability Society Information","authors":"","doi":"10.1109/TR.2024.3400073","DOIUrl":"https://doi.org/10.1109/TR.2024.3400073","url":null,"abstract":"","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"73 2","pages":"C2-C2"},"PeriodicalIF":5.9,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10547143","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141245158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Formal Synthesis of Safety Controllers via $k$-Inductive Control Barrier Certificates","authors":"Tianxiang Ren, Wang Lin, Zuohua Ding","doi":"10.1109/tr.2024.3399739","DOIUrl":"https://doi.org/10.1109/tr.2024.3399739","url":null,"abstract":"","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"30 1","pages":""},"PeriodicalIF":5.9,"publicationDate":"2024-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141152752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Reliable Inventory Management of Key Parts for Wind Turbine Production Under R&D Uncertainty","authors":"Longfei Wang, Miao Zhang, Yifan Zhou, Libin Tan","doi":"10.1109/tr.2024.3394028","DOIUrl":"https://doi.org/10.1109/tr.2024.3394028","url":null,"abstract":"","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"37 1","pages":""},"PeriodicalIF":5.9,"publicationDate":"2024-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141061805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the ability to produce renewable energy sources and control system devices in an adaptive way, smart home systems (SHSs) have significantly improved the quality of our lives. Due to the mission-critical nature and the complex correlations within the system, it is imperative to perform reliability analysis on SHSs. This article studies the reliability of SHSs performing multiphase mission and subject to both common cause failures and cascading behaviors, where the occurrence of common causes would cause failures of multiple components and the failure of a component may further affect other system components in a domino chain manner. In this article, we propose a multivalued decision diagram-based method to assess reliability of phased-mission SHS with cascading common cause effect. The proposed method, applicable to arbitrary time-to-failure distributions, is generalized to reliability analysis of SHSs with multiple repeated operation cycles. Both space and computational complexities of the proposed method are discussed; the correctness is verified using the Monte Carlo simulation method. A detailed case study on an SHS example is performed to illustrate the application and advantages of the proposed method. A sensitivity analysis is carried out to examine the contribution of each component failure to the overall failure of the example SHS.
{"title":"Reliability Analysis of Phased-Mission Smart Home Systems With Cascading Common Cause Failures","authors":"Qian Chen;Chaonan Wang;Quanlong Guan;Jiaqi Shi","doi":"10.1109/TR.2024.3387693","DOIUrl":"10.1109/TR.2024.3387693","url":null,"abstract":"With the ability to produce renewable energy sources and control system devices in an adaptive way, smart home systems (SHSs) have significantly improved the quality of our lives. Due to the mission-critical nature and the complex correlations within the system, it is imperative to perform reliability analysis on SHSs. This article studies the reliability of SHSs performing multiphase mission and subject to both common cause failures and cascading behaviors, where the occurrence of common causes would cause failures of multiple components and the failure of a component may further affect other system components in a domino chain manner. In this article, we propose a multivalued decision diagram-based method to assess reliability of phased-mission SHS with cascading common cause effect. The proposed method, applicable to arbitrary time-to-failure distributions, is generalized to reliability analysis of SHSs with multiple repeated operation cycles. Both space and computational complexities of the proposed method are discussed; the correctness is verified using the Monte Carlo simulation method. A detailed case study on an SHS example is performed to illustrate the application and advantages of the proposed method. A sensitivity analysis is carried out to examine the contribution of each component failure to the overall failure of the example SHS.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 1","pages":"2157-2170"},"PeriodicalIF":5.0,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140840392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Studies on maintenance and inventory optimization have been frequently combined to cut the total operation and maintenance costs of multicomponent systems. Most existing studies assume that components are stochastically independent and only collaborate on inventory management-related resources. In practice, stochastic dependencies exist in most complex systems, and limited maintenance time becomes a crucial resource shared by all components during multimission selective maintenance (SM). Neglecting these features reduces the practicality of policies. To address this limitation, we investigate joint multimission SM and inventory optimization for systems considering stochastic dependency among components. First, an extended factor analysis model incorporating the effects of working conditions is proposed, based on which diverse and dependent degradation processes of components under multiple missions can be well characterized. Then, the sequential optimization of joint multimission SM and inventory policies, which consider information about component degradation states, available resources, and mission profiles simultaneously, is developed using a continuous-state Markov decision process. Decision variables are optimized by an efficient reinforcement learning algorithm. Conclusively, the superiority of the proposed method is illustrated using a numerical example of a photovoltaic system.
{"title":"Joint Multimission Selective Maintenance and Inventory Optimization for Multicomponent Systems Considering Stochastic Dependency","authors":"Xuefeng Kong;Jun Yang;Wenhua Chen;Jun Pan","doi":"10.1109/TR.2024.3389015","DOIUrl":"10.1109/TR.2024.3389015","url":null,"abstract":"Studies on maintenance and inventory optimization have been frequently combined to cut the total operation and maintenance costs of multicomponent systems. Most existing studies assume that components are stochastically independent and only collaborate on inventory management-related resources. In practice, stochastic dependencies exist in most complex systems, and limited maintenance time becomes a crucial resource shared by all components during multimission selective maintenance (SM). Neglecting these features reduces the practicality of policies. To address this limitation, we investigate joint multimission SM and inventory optimization for systems considering stochastic dependency among components. First, an extended factor analysis model incorporating the effects of working conditions is proposed, based on which diverse and dependent degradation processes of components under multiple missions can be well characterized. Then, the sequential optimization of joint multimission SM and inventory policies, which consider information about component degradation states, available resources, and mission profiles simultaneously, is developed using a continuous-state Markov decision process. Decision variables are optimized by an efficient reinforcement learning algorithm. Conclusively, the superiority of the proposed method is illustrated using a numerical example of a photovoltaic system.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"73 4","pages":"1967-1981"},"PeriodicalIF":5.0,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140840614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：