检索结果-内蒙古大学图书馆

Chinese Automation Congress (CAC)

作者： Wen Zhang Jing Wang Ning Wan School of Intelligent Science and Engineering Harbin Engineering University Harbin Heilongjiang

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Model-Agnostic Meta-Learning (MAML), have shown a good generalization performance in solving task planning problems. Most of the existing meta-reinforcement learning(meta-rl) algorithms learn meta-policies by randomly sampling tasks. However, this sampling strategy can only adapt to simple tasks, and have insufficient ability to generalize to difficult and new tasks. To address these problems, the Improved curriculum learning-MAML (ICL-MAML) framework is designed, which the task sampling strategy based on improved curriculum learning is applied for sampling the tasks. This method improves the convergence ability of meta strategies for difficult tasks and their generalization ability for new tasks. At the same time, it alleviates the problem of catastrophic forgetting. Experiments in the meta-world environment show that ICL-MAML has a significant improvement in training and testing success rates, and uses less training time compared to random sampling task strategy.

关键词： Training Metalearning Adaptation models Automation Manipulators Planning Testing Convergence

来源：评论

学校读者我要写书评

暂无评论

Research on Road Target Detection Algorithm Based on Bimodal

Research on Road Target Detection Algorithm Based on Bimodal

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Wenyi Zhang Hongwei Mo School of Intelligent Science and Engineering Harbin Engineering University Harbin China

ISBN: (数字)9798331517090

ISBN: (纸本)9798331517106

With the continuous development of multispectral sensor technology, multispectral detection technology has been widely applied in fields such as intelligent driving. The current main visual detection technologies include visible light and infrared. However, visible light detection faces challenges in adapting to complex environments such as low light conditions, occlusion, and color overlap. On the other hand, infrared images lack detailed texture information and have a high false detection rate. To address the above issues, we propose a detection method that integrates two types of modal feature information. To ensure the speed of model detection, this article selects YOLOX-s as the basic framework and incorporates the CSPNet structure to group features. We design a feature interaction module that combines infrared and visible light information. Finally, an attention fusion module was added to the fusion section, focusing on key features and reducing the interference of redundant information. Experimental results show that the proposed detection algorithm has an average detection accuracy of 79.2% on the FLIR-aligned Dataset. This effectively enhances the robustness and accuracy of object detection in complex scenes, offering promising applications in various domains." effectively improving the robustness and accuracy of object detection in complex scenes, and has good application prospects.

关键词： Hands Visualization Accuracy Image color analysis Roads Object detection Interference Feature extraction Robustness Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Macroporous Directed and Interconnected Carbon Architectures Endow Amorphous Silicon Nanodots as Low‑Strain and Fast‑Charging Anode for Lithium‑Ion Batteries

引用

Nano-Micro Letters 2024年第5期16卷 333-351页

作者： Zhenwei Li Meisheng Han Peilun Yu Junsheng Lin Jie Yu Guangdong Provincial Key Laboratory of Semiconductor Optoelectronic Materials and Intelligent Photonic Systems Shenzhen Engineering Lab for Supercapacitor MaterialsSchool of Material Science and EngineeringHarbin Institute of TechnologyShenzhenUniversity TownShenzhen 518055People’s Republic of China Songshan Lake Materials Laboratory Dongguan Dongguan 523808GuangdongPeople’s Republic of China Department of Mechanical and Energy Engineering Southern University of Science and TechnologyShenzhen 518055People’s Republic of China

Fabricating low-strain and fast-charging silicon-carbon composite anodes is highly desired but remains a huge challenge for lithium-ion ***,we report a unique silicon-carbon composite fabricated by uniformly dis-persing amorphous Si nanodots(SiNDs)in carbon nanospheres(SiNDs/C)that are welded on the wall of the macroporous carbon framework(MPCF)by vertical graphene(VG),labeled as MPCF@VG@SiNDs/*** high dispersity and amor-phous features of ultrasmall SiNDs(~0.7 nm),the flexible and directed electron/Li+transport channels of VG,and the MPCF impart the MPCF@VG@SiNDs/C more lithium storage sites,rapid Li+transport path,and unique low-strain property during Li+***,the MPCF@VG@SiNDs/C exhibits high cycle stability(1301.4 mAh g^(-1) at 1 A g^(-1) after 1000 cycles without apparent decay)and high rate capacity(910.3 mAh g^(-1),20 A g^(-1))in half cells based on industrial electrode *** assembled pouch full cell delivers a high energy density(1694.0 Wh L^(-1);602.8 Wh kg^(-1))and an excellent fast-charging capability(498.5 Wh kg^(-1),charging for 16.8 min at 3 C).This study opens new possibilities for preparing advanced silicon-carbon com-posite anodes for practical applications.

关键词： Amorphous Si nanodots Low-strain Fast-charging Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

A heuristic control framework for heavy-duty hexapod robot over complex terrain

引用

IET Cyber-systems and Robotics 2022年第4期4卷 322-330页

作者： Jinmian Hou Hui Chai Yibin Li Yaxian Xin Wei Chen School of Control Science and Engineering Shandong UniversityJinanChina Engineering Research Center of Intelligent Unmanned System Ministry of EducationShandong UniversityJinanChina

The large and heavy-duty hexapod robot has strong motion stability and load capacity,which promises to have a wide range of application prospects in rescue and disaster ***-mode gait and static stability during walking make the hexapod robot adapt to more diverse terrains,while little research has been conducted on the motion control methods of heavy-duty hexapod robots in complex environments.A novel heuristic whole-body motion control framework for the heavy-duty hexapod robot to traverse complex terrain is *** splitting the legged locomotion into a single task,the whole-body motion could be planned in a reasonable *** terrain adaptation strategy is designed to improve the complex terrain *** reaction forces are then optimised based on single rigid-body dynamics with *** framework utilised simple but powerful heuristics to approximate complex dynamics and allows for a single set of parameters for all task *** results demonstrate the robustness and adaptability of the proposed framework.

关键词： legged locomotion robotics robots

来源：评论

学校读者我要写书评

暂无评论

Optimization of Cluster Transportation Task Scheduling Based on Reinforced Genetic Algorithm

Optimization of Cluster Transportation Task Scheduling Based...

引用

Advanced Algorithms and Control engineering (ICAACE), International Conference on

作者： Jiaqi Li Zhi Zhang Xiaobing Shang School of Intelligent Science and Engineering Harbin Engineering University Harbin China

ISBN: (数字)9798350361445

ISBN: (纸本)9798350361452

In the current highly intelligent environment, how to optimize the material distribution route with more intelligent and effective methods before the task starts to be executed to achieve better task allocation has become the key to reduce one's own cost and improve the rate of return, and it is also a major challenge. In order to solve this problem well, this paper proposes a reinforced genetic algorithm (RGA) which combines Levy flight and Q-learning reinforcement learning method to optimize the task scheduling scheme in the process of material distribution. The variant of the multi-traveling salesman problem is used as a model to test the performance of the algorithm. According to the experimental results, by introducing Q-learning to dynamically adjust the crossover and mutation probability, and introducing Levy flight strategy for auxiliary optimization, the proposed method can get the optimal solution more easily. Therefore, the proposed algorithm has excellent optimization ability and stability, and it is easier to get a reasonable task scheduling method when applied, and it can effectively reduce the distribution cost.

关键词： Q-learning Costs Heuristic algorithms Sociology Scheduling Stability analysis Resource management

来源：评论

学校读者我要写书评

暂无评论

Research on Data-Driven Transient Stability Assessment Method for Ship Power systems

Research on Data-Driven Transient Stability Assessment Metho...

引用

IEEE Conference and Expo Transportation Electrification Asia-Pacific (ITEC Asia-Pacific)

作者： Ziwei Song Fang Lu School of Intelligent Science and Engineering Harbin Engineering University Harbin China

ISBN: (数字)9798331529277

ISBN: (纸本)9798331529307

As the scale of ship power systems expands, it becomes increasingly necessary to quickly and accurately assess the transient stability of the system to ensure its safe operation. In recent years, data-driven artificial intelligence (AI) methods have gained attention for their speed, accuracy, and strong generalization capabilities. Given the current limitations in utilizing existing specialized software to perform precise transient calculations for ship power systems, this study establishes a comprehensive mathematical model of the ship power system. Time-domain simulations under various disturbances are conducted to build a dataset for training neural networks. A neural network classification model combining a denoising autoencoder (DAE) and a long short-term memory (LSTM) network is developed to achieve real-time transient stability assessment of ship power systems. To address the decline in model performance under different operating conditions and the time-consuming process of re-collecting data and retraining models, transfer learning (TL) is employed for the transient stability assessment of ship power systems.

关键词： Accuracy Stability criteria Transfer learning Power system stability Data models Mathematical models Marine vehicles Transient analysis Thermal stability Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Dynamic Constitutive Model and Numerical Simulation of S32760 Duplex Stainless Steel Based on Dislocation Theory

引用

Recent Patents on Mechanical engineering 2024年第2期17卷 105-115页

作者： Yang, Lin Zhang, Heqing Zheng, Minli Zhang, Xiangyuan Liu, Jialiang Liu, Yinfeng Gong, Fukang Key Laboratory of Advanced Manufacturing and Intelligent Technology Ministry of Education Harbin University of Science and Technology Harbin150080 China Qiqihar Heavy CNC Equipment Co. Ltd. Qiqihar161005 China School of Mechanical and Electrical Engineering Qiqihar University Qiqihar161005 China

Background: To describe the complex mechanical behavior of S32760 duplex stainless steel under high strain rate and high-temperature loading conditions. Objective: The constitutive model of S32760 duplex stainless steel suitable for high strain rate was constructed from the micro-scale. Methods: Based on the theory of dislocation dynamics, the effects of different strain rates and strains on the plastic deformation of ferrite and austenite were analyzed, and the thermal stress term and non-thermal stress term of ferrite and austenite phases were coupled. Results: The simulation results of the model show that the S32760 dual-phase constitutive model has a high degree of fit with the experimental data at high strain rates. Conclusion: Compared with the classical J-C model, the results show that the constitutive model of this patent has more accurate predictability than the J-C model in describing the mechanical behavior of duplex stainless steel in the high strain range of 5000s-1 to 10000s-1. © 2024 Bentham science Publishers.

关键词： Constitutive models

来源：评论

学校读者我要写书评

暂无评论

Resilient Event-Triggered Model Predictive Control for Adaptive Cruise Control Under Sensor Attacks

引用

IEEE/CAA Journal of Automatica Sinica 2023年第3期10卷 807-809页

作者： Zhijian Hu Rong Su Kai Zhang Zeyuan Xu Renjie Ma School of Electrical and Electronic Engineering Nanyang Technological UniversitySingapore 639798Singapore Key Laboratory of Ultra-Precision Intelligent Instrumentation Ministry of Industry and Information Technologyand the Center of Ultra-Precision Optoelectronic Instrument EngineeringHarbin Institute of TechnologyHarbin 150001China Department of Control Science and Engineering Harbin Institute of TechnologyHarbin 150001China Department of Chemical and Biomolecular Engineering National University of SingaporeSingapore 117585Singapore State Key Laboratory of Robotics and Systems Harbin Institute of TechnologyHarbin 150001China IEEE

Dear Editor,This letter addresses the resilient model predictive control(MPC)problems for adaptive cruise control(ACC)systems under sensor *** the light of vulnerabilities of ACC systems to sensor attacks,an intrusion detection mechanism is proposed at the controller side to distinguish abnormal ***,the robust control gains are derived to design the terminal region constraint for MPC.

关键词： Trigger Event constraint

来源：评论

学校读者我要写书评

暂无评论

Attention Enhanced Feature Fusion for Mental Stress Level Classification 21

Attention Enhanced Feature Fusion for Mental Stress Level Cl...

引用

21st International Computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2024

作者： Sahlu, Ameneshewa Abush Yohannes, Gobena Mulugeta Dawit, Bekalu Nigus Teshome, Molla Woretaw School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan Chengdu China School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu China

ISBN: (纸本)9798331519254

Mental stress poses significant health risks, manifesting in various psychological and physical issues such as depression, anxiety, and cardiovascular complications. Establishing a reliable method for swiftly and accurately classifying mental stress levels is crucial due to its widespread impact. Existing classification approaches predominantly rely on either data-intensive traditional machine learning algorithms or opaque deep learning models, hindering real-world use and interpretability. This study addresses these limitations by proposing a novel approach for stress level classification using the WESAD dataset. Our method combines an attention-based ResN et with CBAM. This innovative approach synergistically integrates shallow and deep features, harnessing both low-level details and high-level semantic information to effectively classify stress levels into four distinct states: baseline, stress, amusement, and meditation, or three states excluding the meditation state. The experimental result shows 92.74% accuracy and 91.19% F1 score for the 4-class setup, and 97.58% accuracy and 97.51 % F1 score for the 3-class setup. Our approach offers a more robust and interpretable framework for mental stress classification, with potential applications in health care and stress management. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Recent Patents on Bearing Pre-tightening

引用

Recent Patents on engineering 2022年第1期16卷 59-70页

作者： Zhao, Yanling Zhang, Jiashuo Key Laboratory of Advanced Manufacturing and Intelligent Technology Ministry of Education Harbin University of Science and Technology Harbin150080 China School of Mechanical and Power Engineering Harbin University of Science and Technology 150080 China

Background: Bearing has been widely used in automotive, aerospace, electronics industry and other fields. Its pre-tightening technology is one of the most critical technologies. It has an important influence on the accuracy, speed, stiffness and temperature rise of the spindle. Proper pre-tightening force can eliminate bearing clearance and improve machining accuracy and efficiency of machine tools. Therefore, the development trend of bearing pre-tightening mechanism has been paid more and more attention. Objective: In order to improve the processing efficiency and processing accuracy of the bearing system, the structure and function of the bearing pre-tensioning device are continuously enhanced. Methods: This paper retraces various current representative patents relative to the mechanism of bearing pre-tightening. Results: Through the investigation of a number of patents of bearing pre-tightening devices, the principles and effects of different bearing pre-tightening devices are classified and reviewed. Be-sides, the future development trend of bearing pre-tightening devices is discussed. Conclusion: The optimization of the bearing pre-tightening device is conducive to improving processing efficiency and quality. A controllable pre-tightening force is the research direction, and more related patents will be invented in the future. © 2022 Bentham science Publishers.

关键词： Efficiency

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：