检索结果-内蒙古大学图书馆

27th ieee International conference on Intelligent Transportation systems, ITSC 2024

作者： Bejarbaneh, Elham Yazdani Du, Haiping Naghdy, Fazel School of Electrical Computer and Telecommunications Engineering University of Wollongong WollongongNSW2500 Australia

ISBN: (纸本)9798331505929

Platooning control of connected and automated vehicles (CAVs) has emerged as a promising strategy to enhance fuel economy, traffic efficiency and safety. One of the main challenges in coordinating multiple vehicles is executing safe and efficient cooperative control, while considering the inherent nonlinearities in vehicle dynamics. This study aims to design a data-driven optimal distributed leader-tracking control for heterogeneous vehicle platoon in the traffic scenario. Every vehicle within the platoon is treated as a multi-input-multi-output system, exhibiting nonlinear dynamics. The distributed control system is developed using reinforcement learning (RL) algorithm that learns the optimal control policies from the vehicle system data without requiring prior knowledge of vehicle dynamics. This method ensures that all platoon vehicles reliably follow the leader's behaviour, even in the presence of unknown and nonlinear dynamics. Simulation results involving a platoon of heterogeneous and nonlinear CAVs demonstrate the effectiveness of the proposed cooperative controller. © 2024 ieee.

关键词： control nonlinearities

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Domain Adaptation with Feature Separation for Wind Turbine Anomaly Detection 13

Semi-Supervised Domain Adaptation with Feature Separation fo...

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Ming, Guangqiang Ma, Shihao Xu, Junyang Wang, Jiaye Jia, Zhenwei Zhao, Chunhui Powerchina Huadong Engineering Corporation Ltd. Hangzhou311122 China College of Control Science and Engineering Zhejiang University Hangzhou310027 China Institute of Intelligence Science and Engineering Shenzhen Polytechnic University Shenzhen518055 China

ISBN: (纸本)9798350361674

Anomaly detection for the wind power generation process is important for the maintenance and early warning of wind turbines. Deep learning-based methods are widely used in wind turbine anomaly detection. However, the data distribution changes frequently due to the changing working conditions of wind turbines, and deep learning methods are difficult to directly apply to new working conditions with scarce labeled data. Therefore, this paper proposes a semi-supervised domain adaptation method with feature separation (SSDA-FS) for wind turbine anomaly detection. First, a feature separation domain adaptation strategy is designed to eliminate inter-domain differences. The feature space is decomposed into domain-related space and anomaly-related space through the devised adversarial training. Then a semi-supervised timing augment strategy is proposed, which can augment the unlabeled samples and a few labeled samples in the target domain. The proposed method is implemented and validated in a wind turbine anomaly detection dataset, and the performance is significantly improved compared with the comparison methods. © 2024 ieee.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of data-driven learning control: An Optimization-Based Approach

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND learning systems 2022年第10期33卷 5527-5541页

作者： Meng, Deyuan Zhang, Jingyao Beihang Univ BUAA Res Div 7 Beijing 100191 Peoples R China Beihang Univ BUAA Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China

learning to perform perfect tracking tasks based on measurement data is desirable in the controller design of systems operating repetitively. This motivates this article to seek an optimization-based design and analysis approach for data-driven learning control systems by focusing on iterative learning control (ILC) of repetitive systems with unknown nonlinear time-varying dynamics. It is shown that perfect output tracking can be realized with updating inputs, where no explicit model knowledge but only measured input-output data are leveraged. In particular, adaptive updating strategies are proposed to obtain parameter estimations of nonlinearities. A double-dynamics analysis approach is applied to establish ILC convergence, together with boundedness of input, output, and estimated parameters, which benefits from employing properties of nonnegative matrices. Simulations are implemented to verify the validity of our optimization-based adaptive ILC.

关键词： Convergence Adaptation models Trajectory Task analysis Indexes Adaptive systems Time-varying systems Adaptive updating data-driven learning control iterative learning control (ILC) nonlinear system nonnegative matrix optimization-based design and analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing Automata learning with Statistical Machine learning: A Network Security Case Study 24

Enhancing Automata Learning with Statistical Machine Learnin...

引用

27th International conference on Model driven Engineering Languages and systems (MODELS)

作者： Ayoughi, Negin Nejati, Shiva Sabetzadeh, Mehrdad Saavedra, Patricio Univ Ottawa Ottawa ON Canada RabbitRun Technol Inc Etobicoke ON Canada

ISBN: (纸本)9798400705045

Intrusion detection systems are crucial for network security. Verification of these systems is complicated by various factors, including the heterogeneity of network platforms and the continuously changing landscape of cyber threats. In this paper, we use automata learning to derive state machines from network-traffic data with the objective of supporting behavioural verification of intrusion detection systems. The most innovative aspect of our work is addressing the inability to directly apply existing automata learning techniques to network-traffic data due to the numeric nature of such data. Specifically, we use interpretable machine learning (ML) to partition numeric ranges into intervals that strongly correlate with a system's decisions regarding intrusion detection. These intervals are subsequently used to abstract numeric ranges before automata learning. We apply our ML-enhanced automata learning approach to a commercial network intrusion detection system developed by our industry partner, RabbitRun Technologies. Our approach results in an average 67.5% reduction in the number of states and transitions of the learned state machines, while achieving an average 28% improvement in accuracy compared to using expertise-based numeric data abstraction. Furthermore, the resulting state machines help practitioners in verifying system-level security requirements and exploring previously unknown system behaviours through model checking and temporal query checking. We make our implementation and experimental data available online.

关键词： State-machine learning Intrusion detection Decision trees Denial of Service (DoS) attacks Model checking Query checking

来源：评论

学校读者我要写书评

暂无评论

Cooperative Awareness Message Generation Interval Prediction Model Based on Bayesian Optimized Long Short-Term Memory Neural Network 13

Cooperative Awareness Message Generation Interval Prediction...

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Zhang, Xiaoping Feng, Hui Wang, Li School of Electrical and Control Engineering North China University of Technology Beijing100044 China University of Cambridge Department of Engineering CambridgeCB2 1PZ United Kingdom

ISBN: (纸本)9798350361674

The prediction accuracy of the generation interval of Cooperative Awareness Message (CAM) is known to directly affect the accuracy of reserved communication resources for CAM in cellular vehicle-to-everything (C-V2X) systems. In order to improve the prediction accuracy of CAM generation interval, a prediction model based on the Bayesian optimized long short-term memory neural network (BAO-LSTM) is proposed. The model utilizes LSTM to predict the generation interval of CAM while employing the Bayesian optimization algorithm iteratively to optimize the hyperparameters of LSTM until they reach their optimal values. The pre-processed Next Generation Simulation (NGSIM) dataset is used to verify the performance of the BAO-LSTM model. Experimental results demonstrate that the BAO-LSTM model outperforms both of the BP model and the LSTM model without the Bayesian optimization process in terms of capturing, and constructing patterns and rules for the generation time interval of CAM. © 2024 ieee.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Intrinsic Motivation Exploration via Self-supervised Prediction in Reinforcement learning 6

Intrinsic Motivation Exploration via Self-supervised Predict...

引用

6th International conference on data-driven Optimization of Complex systems (DOCS)

作者： Yang, Zhiyou Du, Hongfei Wu, Yunhan Jiang, Zhuotong Qu, Hong Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Sichuan Peoples R China

ISBN: (纸本)9798350377859;9798350377842

In many real-world scenarios, extrinsic rewards available to the agent are exceedingly sparse. In such cases, curiosity can serve as an intrinsic reward signal, motivating the agent to explore its environment and acquire skills that could prove valuable in the future. Hence, exploration based on information novelty has brought great success in challenging reinforcement learning problems with sparse rewards. In this paper, we propose an exploration strategy, called Intrinsic Motivation Exploration (IME), that distills task-relevant information from raw state-action pairs using a self-supervised inverse dynamics model. Our exploration bonus is quantified as the compressiveness of raw state-action pairs with respect to the learned representation of the forward model. Through extensive experiments on continuous control benchmarks, we demonstrate that our IME method learns an effective exploration strategy by robustly measuring the novelty of raw state-action pairs in several control environments.

关键词： Intrinsic motivation Policy exploration Self-supervised prediction

来源：评论

学校读者我要写书评

暂无评论

Research on Blood Glucose Nonlinear controller Based on Backstepping Adaptive control Algorithm 13

Research on Blood Glucose Nonlinear Controller Based on Back...

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Liu, Shuya Song, Ruizhuo Lu, Xiang Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China Automation and Electrical Engineering Beijing Institute of Technology Beijing100083 China

ISBN: (纸本)9798350361674

Closed-loop control of blood glucose regulation in type 1 diabetes patients can be achieved through an artificial pancreas. In this article, a nonlinear controller based on backstepping adaptive approach is proposed for the integration of the artificial pancreas, with a focus on improving the effectiveness of postprandial blood glucose control. By extending the Bergman physiological model using a digestion kinetics equation, an extended blood glucose dynamic model is established to effectively capture the relationship between meal intake and blood glucose variations. The blood glucose model, which includes personalized unknown parameters, serves as the basis for the derivation of the control algorithm using a combination of backstepping control and adaptive control algorithms. By accurately calculating the required dosage and timing of insulin injections for individual patients, the designed control algorithm enables precise blood glucose control. The resulting control signal, capable of adapting to unknown parameters, effectively regulates fasting and postprandial blood glucose levels in type 1 diabetes patients. The effectiveness and robustness of the proposed blood glucose control algorithm are demonstrated through the implementation of various experimental protocols. © 2024 ieee.

关键词： Physiological models

来源：评论

学校读者我要写书评

暂无评论

Decentralized control on High-Speed Trains Based on State Observation 13

Decentralized Control on High-Speed Trains Based on State Ob...

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Dong, Xudong Zhang, Jilie School of Information Science and Technology Southwest Jiaotong University Chengdu611756 China

ISBN: (纸本)9798350361674

It is well known that the dynamic model of high-speed trains are difficult to be accurately modeled, due to the air resistance shows nonlinear characteristics, and other resistances also be obtained by some empirical formulas. The above resistances are regarded as a real-time disturbance for train. Hence it has a significant adverse impact on train operation. Here, a cooperative controller based on a expansion state observation is proposed to estimate these resistances. The proposed control allows each car to be controlled asynchronously according to the railroad conditions in order to achieve high tracking performance of the speed profile and minimization of internal forces, which will greatly improve the punctuality and safety of high-speed trains. In addition, the observer is also designed based on a reduced-order system to reduce the design parameters. Train and coupler lengths are also considered to fully analyze the train dynamics associated with interaction forces as the train passes through complex road conditions. © 2024 ieee.

关键词： Decentralized control

来源：评论

学校读者我要写书评

暂无评论

data-driven Reinforcement learning for Optimal Motor control in Washing Machines 2

Data-Driven Reinforcement Learning for Optimal Motor Control...

引用

2nd ieee conference on Artificial Intelligence (CAI)

作者： Kang, Chanseok Bae, Guntae Kim, Daesung Lee, Kyoungwoo Son, Dohyeon Lee, Chul Lee, Jaeho Lee, Jinwoo Yun, Jae Woong LG Elect AI Lab Seoul South Korea

ISBN: (纸本)9798350354102;9798350354096

In this paper, we address the challenge of developing advanced motor control systems for modern washing machines, which are required to operate under various conditions. Traditional system designs often rely on manual trial-and-error methods, limiting the potential for performance enhancement. To overcome this, we propose a novel continual offline reinforcement learning framework, specifically tailored to improve balance maintenance during the dehydration cycle of washing machines. Our approach introduces a delayed online update mechanism that leverages accumulated transition data from certain periods of online interaction. This method effectively circumvents the distribution shift problem commonly encountered in offline reinforcement learning. Our empirical results demonstrate a substantial improvement, with an average increase of nearly 16% in load balancing efficiency across various tasks, including those involving different types of laundry. This research not only enhances the applicability of reinforcement learning in industrial settings but also represents a significant step forward in the development of smart appliance technology.

关键词： Washing Machine Offline RL Industrial AI

来源：评论

学校读者我要写书评

暂无评论

Photogrammetry-driven Detection of Structural Peeling in Joints and Corners of Rigid Pavements Using an Unsupervised learning Meta-Architecture

引用

ieee ACCESS 2025年 13卷 48132-48145页

作者： Cruz, Jose Calsina, Helarf Huacasi, Luis Mamani, Wilson Beltran, Norman Puma, Flavio Yana-Mamani, Victor Huaquipaco, Saul Univ Nacl Altiplano Puno 21001 Peru Univ Nacl Juliaca Juliaca 21101 Peru Univ Continental Arequipa 04002 Peru Univ Alicante Alicante 03690 Spain Univ Nacl Moquegua Perane 18611 Peru

This study proposes the SS-XceVNet meta-architecture, which integrates Xception and VGG16 to detect structural peeling in rigid pavements in an automated manner, thereby reducing the reliance on large, labeled datasets. With increasing traffic and exposure to environmental factors, failures in rigid pavement joints and corners are becoming increasingly frequent, making manual inspections time consuming, dangerous, and subjective. To address this problem, a method was developed in four phases. First, photogrammetry and data augmentation techniques are used to collect and increase the variety of images. Self-supervised learning was then applied to unlabeled data to reduce reliance on manual annotations. SS-XceVNet was then trained on labeled data, combining the robustness of Xception and VGG16 to refine the accuracy. Finally, the results were compared with those of the XceVNet-based model. Evaluations showed that SS-XceVNet achieved 80.43% accuracy, surpassing 47.83% of the base model. This underscores the usefulness of self-supervised learning and integration of advanced architectures in pavement failure detection. In conclusion, this approach improves efficiency in the functional evaluation of road infrastructures while reducing costs and occupational risks, laying the foundation for future research that contributes to the implementation of proactive maintenance systems. Automated detection thus strengthens the quality control of pavements, favoring road safety, and prolonging the useful life of roads.

关键词： Accuracy Roads YOLO Maintenance Feature extraction Unsupervised learning Manuals Training Inspection Deep learning Photogrammetry rigid pavements unsupervised learning VGG16 Xception

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：