检索结果-内蒙古大学图书馆

Multi-state system reliability:An emerging paradigm for sophisticated engineered systems

Frontiers of engineering Management 2024年第3期11卷 568-575页

作者： Yu LIU Tangfan XIAHOU Qin ZHANG Liudong XING Hong-Zhong HUANG School of Mechanical and Electrical Engineering University of Electronic Science and Technology of ChinaChengdu 611731China Center for System Reliability and Safety University of Electronic Science and Technology of ChinaChengdu 611731China Department of Electrical&Computer Engineering University of Massachusetts DartmouthMA 02747USA

1 Introduction Reliability is defined as the probability that a system or component will perform its required function for a specified period of time under specified operating conditions(Ebeling,2019).Traditional reliability theory assumes that both a system and its components have only two possible states in the operation stage,either perfectly functioning or completely ***,as engineered systems become more sophisticated,involving larger sizes,increased functionality,and greater intelligence,and with advancements in sensing technologies,it has been extensively observed that systems and components exhibit multiple distinct states as they deteriorate over *** failure behavior,damage severity,performance capacity,and operational efficiency of the system and components vary among these states(Lisnianski et al.,2018).It,therefore,necessitates the development of advanced reliability theories and methodologies that are capable of characterizing these systems and components with multi-state nature.

关键词： system state specified

来源：评论

学校读者我要写书评

暂无评论

DPN: Decoupling Partition and Navigation for Neural Solvers of Min-max Vehicle Routing Problems 41

DPN: Decoupling Partition and Navigation for Neural Solvers ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zheng, Zhi Yao, Shunyu Wang, Zhenkun Tong, Xialiang Yuan, Mingxuan Tang, Ke Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China China Huawei Noah's Ark Lab Shenzhen China

The min-max vehicle routing problem (min-max VRP) traverses all given customers by assigning several routes and aims to minimize the length of the longest ***, reinforcement learning (RL)-based sequential planning methods have exhibited advantages in solving efficiency and ***, these methods fail to exploit the problem-specific properties in learning representations, resulting in less effective features for decoding optimal *** paper considers the sequential planning process of min-max VRPs as two coupled optimization tasks: customer partition for different routes and customer navigation in each route (i.e., partition and navigation).To effectively process min-max VRP instances, we present a novel attention-based Partition-and-Navigation encoder (P&N Encoder) that learns distinct embeddings for partition and ***, we utilize an inherent symmetry in decoding routes and develop an effective agent-permutation-symmetric (APS) loss *** results demonstrate that the proposed Decoupling-Partition-Navigation (DPN) method significantly surpasses existing learning-based methods in both single-depot and multi-depot minmax *** code is available at. Copyright 2024 by the author(s)

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

GIRP: Energy-Efficient QoS-Oriented Microservice Resource Provisioning via Multi-Objective Multi-Task Reinforcement Learning

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 5793-5807页

作者： Yuan, Honggang Wang, Ting Fu, Min Shi, Yuanming East China Normal University MoE Engineering Research Center of Software/Hardware Co-design Technology and Application Shanghai Key Laboratory of Trustworthy Computing Shanghai200062 China National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore ShanghaiTech University School of Information Science and Technology Shanghai201210 China

Microservice architecture has revolutionized web service development by facilitating loosely coupled and independently developable components distributed as containers or virtual machines. While existing studies emphasize end-to-end latency, this paper investigates energy-efficient quality-of-service (QoS)-oriented microservice provisioning, focusing on both QoS satisfaction and power consumption (PC) conservation. We propose the Green and Intelligent Resource Provision (GIRP) architecture, integrating a data-driven energy-latency-aware resource allocation and scheduling manager to balance latency and PC. To reconcile the trade-offs involved, a dual-objective optimization problem is formulated to minimize latency and energy use by selecting proper servers, allocating CPU cores, and determining service replicas. To address challenges with discrete variables, dual objectives, and implicit mappings, we leverage a model-free deep deterministic policy gradient-based reinforcement learning algorithm. Specifically, we develop a multi-task agent via the Multi-gate Mixture-of-Experts model to simultaneously make two separate actions regarding CPU core numbers and service replica numbers, followed by a single-task agent to determine service scheduling. Extensive experiments on the DeathStarBenchmark testbed validate GIRP's effectiveness, demonstrating approximately 52% resource savings and a 43% reduction in PC compared to leading methods like Sinan, Firm, and heuristic-based algorithms. These results highlight GIRP's capability to optimize microservice orchestration by balancing end-to-end latency and power efficiency. © 2025 IEEE. All rights reserved.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

A Proposed Mala-Net CNN Algorithm for Malaria Early Detection Based on Thick Blood Smear 2

A Proposed Mala-Net CNN Algorithm for Malaria Early Detectio...

引用

2nd International Symposium on Information Technology and Digital Innovation, ISITDI 2024

作者： Indra, Zul Jusman, Yessi Elfizar Mahdiyah, Evfi Salambue, Roni Winarso, Doni Universitas Riau Departement of Computer Science Pekanbaru Indonesia Universitas Muhammadiyah Yogyakarta Departement of Electrical Engineering Bantul Indonesia Universitas Muhammadiyah Riau Departement of Information System Pekanbaru Indonesia

ISBN: (纸本)9798350389241

Malaria has spread worldwide since the early 20th century and causes nearly half a million deaths each year. Malaria is actually not a dangerous disease and can be easily cured if the treatment can be carried out effectively. Therefore, efforts to identify the presence of the plasmodium parasite early will greatly help reduce the death rate caused by this disease. However, the fact is that this disease often does not get serious attention. Generally, this disease is only treated in the critical phase because it is considered just a common flu. This research is intended to produce a computer-aided disease diagnosis (CAD) system enriched with CNN algorithms to assist in early malaria diagnosis. This CAD system is expected to provide an effective and reliable malaria diagnosis, and avoid the limitations of manual diagnosis. In order to develop the CAD applications, this study proposed a novel CNN architecture called as Mala-Net by utilizing red thick blood dataset. In conclusion, this study successfully surpassed previous studies used as benchmarks with an accuracy value above 97%. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Research on Causal Model Construction and Fault Diagnosis of Control systems 7th

Research on Causal Model Construction and Fault Diagnosis of...

引用

7th International Conference on Computing, Control and Industrial engineering, CCIE 2023

作者： Zhu, Qun Chen, Zhi Liu, Jie Xu, Zhuoran Wen, Juan Yang, Jinghua Jian, Yifan School of Computer Science University of South China Hengyang421200 China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu610064 China School of Electrical Engineering University of South China Hengyang421200 China

ISBN: (纸本)9789819927296

Fault diagnosis of complex control systems is a difficult and hot topic of research at this stage. In order to explore the internal operation characteristics of complex control systems and fault propagation methods to achieve efficient and accurate fault diagnosis, this paper studies control system fault diagnosis methods based on cause-effect relationships, analyzes the role relationship between system components from the perspective of control equation structure, proposes the method of constructing cause-effect diagram models with control equations, and uses the algorithm of way to implement, and then combine the information flow to quantify the causal effect quantifiably, when the system steady state is disrupted, the information flow produces a jump, so as to extend the fault diagnosis reasoning method. The fault diagnosis is verified by simulation of the pressure control system of the nuclear power plant regulator, and the experimental results verify the effectiveness of the proposed method. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Characteristic Analysis of a Cylindrical Linear Motor for Drive Mechanism 26

Characteristic Analysis of a Cylindrical Linear Motor for Dr...

引用

26th International Conference on electrical Machines and systems, ICEMS 2023

作者： Niu, Xu Yu, Tianda Zhang, Lu Zhang, He Harbin Institute of Technology School of Electrical Engineering Harbin China Nuclear Power Institute of China Science and Technology on Reactor System Design Technology Laboratory Chengdu China

ISBN: (纸本)9798350317589

The control rod drive mechanism (CRDM) is a critical device in nuclear plants. This paper proposes a kind of CRDM applying the cylindrical linear induction motor (CLIM). First, the structure and the working principle are introduced. Second, the finite-element method (FEM) is applied to analyze the electromagnetic characteristics of CRDM. The lifting force variation curves with different electromagnetic and structural parameters are obtained. Third, the thermal analysis is carried out by FEM. The steady-state thermal distribution and temperature of each component of CRDM are obtained. All the above results show that the proposed CRDM can meet the design criteria and such functions as rising, falling, and holding still. © 2023 IEEE.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

PATH OPTIMIZATION FOR DYNAMIC OBSTACLE AVOIDANCE OF PIONEER ROBOT BASED ON DDPG SMART AGENT

引用

UPB Scientific Bulletin, Series D: Mechanical engineering 2023年第2期85卷 29-42页

作者： Zheng, Qingchun Peng, Zhi Zhu, Peihao Zhao, Yangyang Ma, Wenpeng Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin University of Technology Tianjin300384 China China School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China

To improve the path efficiency for dynamic obstacle avoidance algorithms of Pioneer robots, this paper proposes an approach to create deep deterministic policy gradient (DDPG) smart agents with recurrent neural networks (RNN) to optimize the path strategy. This approach is realized by training RNN with the backpropagation (BP) algorithm to train the agent. First, the SolidWorks model and obstacle avoidance model of the Pioneer robot is established. The LIDAR sensor is used to obtain environmental information. Further, deep reinforcement learning obstacle avoidance algorithm based on RNN is presented. The dynamic obstacle avoidance path of the Pioneer robot is further simulated in two different virtual robot experiment platform (V-REP) scenarios. The simulation results show that the proposed algorithm shortens the training time by 26.3% compared with the DDPG algorithm. Our proposed scheme can improve the path efficiency for dynamic obstacle avoidance of the Pioneer robot. © 2023, Politechnica University of Bucharest. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Meteorology Predicting Technology Based on Artificial Intelligence Algorithms

Meteorology Predicting Technology Based on Artificial Intell...

引用

2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent systems, ICETSIS 2024

作者： Abitova, Gulnara Mukashev, Daniyar Aitmukhanbetova, Elvira Rakhimzhanova, Mira Uskenbayeva, Gulzhan Kulniyazova, Korlan Binghamton University Dept Electrical Engineering and Computer Science Binghamton United States Astana It University Dept. of Computer Engineering Astana Kazakhstan L.N. Gumilyov Eurasian National University Dept. System Analysis and Management Astana Kazakhstan

ISBN: (纸本)9798350372229

The research explores the transformative impact of Artificial Intelligence in meteorology, weather forecasting. The study presented historical prediction methods overview, evolution highlighting from traditional models to advanced AI-driven systems. It delves into the integration of machine and deep learning techniques in data analysis, emphasizing technologies that significantly enhanced the accuracy and efficiency of weather predictions. Key aspects covered include the neural networks application in interpreting complex atmospheric data, the big data role in providing comprehensive training sets for AI models, the predictive analytics utilization for short-term and long-term weather forecasts. The study also examines case-study with AI implemented in weather forecasting, capability demonstrating in handling extreme weather events and climate anomalies. The study addresses the challenges and limitations faced in the meteorology AI integration, such as data quality concerns, computational requirements, and the specialized expertise need. It proposes potential solutions, future directions for research domain, suggesting a multidisciplinary approach involving meteorologists, data scientists, and AI experts. The conclusion underscores the revolutionary impact of AI-technology in meteorology, projecting how continuous advancements in AI-technology could redefine the predicting weather patterns approach. The work highlights the AI current state in weather forecasting but also sets the future innovations stage. © 2024 IEEE.

关键词： artificial intelligence data analysis machine learning neural networks predictive analytics weather Forecasting

来源：评论

学校读者我要写书评

暂无评论

Research on Cylindrical Linear Induction Motor for Drive Mechanism 14

Research on Cylindrical Linear Induction Motor for Drive Mec...

引用

14th International Symposium on Linear Drivers for Industry Applications, LDIA 2023

作者： Niu, Xu Yu, Tianda Zhang, Lu Li, Qingzhao Huang, Siyu Liu, Yanting Wu, Hao Tang, Yuan School of Electrical Engineering Harbin Institute of Technology Harbin China Nuclear Power Institute of China Science and Technology on Reactor System Design Technology Laboratory Chengdu China

ISBN: (纸本)9798350329612

The control rod drive mechanism (CRDM) is a kind of servo mechanism for the reactor control system of the nuclear power plant. This paper presents a cylindrical linear induction motor suitable for the CRDM. First, the structure of the CRDM is introduced. Second, the relationship between the main dimensions and the electromagnetic load is derived. Third, the influence of materials of the mover shielding shell, speed, and electromagnetic parameters on the lifting force is analyzed by the finite-element method (FEM). Meanwhile, the steady-state temperature of each component of the CRDM is obtained. Finally, a scaled-down prototype is manufactured to verify the rationality of the design. The test results show that the FEM results are consistent with the experimental results, and the essential functions such as lifting, lower insertion, and maintenance can be realized. © 2023 IEEE.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

Insights into the Future: XAI Integration in O-RAN and Space Communication systems

Insights into the Future: XAI Integration in O-RAN and Space...

引用

2024 Multimedia University engineering Conference, MECON 2024

作者： Tahir, H. Ahmed Nabi, Fahad Tariq, Muhammad Ziad Khan, Ahmad Fasih Mahmud, Azwan Multimedia University Faculty of Engineering Cyberjaya Malaysia University of Kiel Department of Electrical Engineering & Information Technology Kiel Germany Department of Computer Science SZABIST University Islamabad Pakistan Roots School System Islamabad Pakistan

ISBN: (纸本)9798331530747

This paper outlines the merging of Explainable Artificial Intelligence (XAI) with Open Radio Access Network (O-RAN) and space communication systems. The usage of AI drives decision-making in critical domains of telecommunications and space explorations requires transparency and interpretability. However, traditional AI models often operate as 'black boxes,' making it difficult to understand their decision-making processes. This lack of explainability poses significant risks, including misinterpretation of signals, undetected anomalies, and erroneous decision-making, which can compromise the integrity of communication systems. Specifically, the challenges include accurately distinguishing between legitimate signals and attacks in anti-jamming scenarios, understanding the behaviour of complex models like LSTM in traffic prediction, and ensuring the reliability of telemetry data despite errors and noise. Integration of XAI techniques within O-RAN architecture and space communication protocols can ensure trust, reliability and safety in AI-enabled systems. This paper investigates the opportunities and challenges of incorporating XAI in O-RAN and space communications. Additionally, it presents the implications of XAI, the need for interpretability in autonomous spacecraft operations, anomaly detection and decision support for mission-critical tasks. By bridging the gap in AI transparency and advanced communication technology, this paper aims to present a detailed analysis of implemented AI and Machine Learning (ML) in the telecommunication domain. It also presents the challenges currently faced in the intersection of XAI and communication. Use cases of XAI in the domain of Open Radio Access Network and Space Communications in light of LIME and SHAP techniques were presented to give a hypothetical modelling for future experimentation to provide local and global interpretation and explanations for the currently employed AI/ML models in the respective domains. Overall, this

关键词： Radio access networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：