检索结果-内蒙古大学图书馆

4th IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2024

作者： Song, Wei Guo, Yu Ning, Keqing Guo, Wei North China University of Technology School of Information Science and Technology Beijing China North China University of Technology School of Electrical and Control Engineering Beijing China

ISBN: (纸本)9798350363586

It is crucial to balance accuracy and beyond-accuracy indicators in recommendations through multi-objective optimization (MOO) methods. Existing multi-objective recommendation methods have several issues: they cannot dynamically model users' long-term and short-term preferences;they fail to solve non-convex problems and are prone to getting stuck in local optima;they neglect the issues of diversity and novelty in recommendations, etc. Therefore, this paper proposes using multi-objective reinforcement learning (MORL) to address the trade-off between accuracy, diversity, and novelty in course recommendation. First, dynamic modeling of users' long-term and short-term interest preferences is conducted using user feature information, course feature information, and users' historical course features. Second, the Actor-Critic network is applied to course recommendation, and a multi-layer reward function and Q-value function are introduced to learn multiple objectives simultaneously. Diversity and novelty assessment indicators are also added to measure the effectiveness of course recommendations Finally, experiments are conducted on three real MOOC datasets, proving the superior performance of the proposed course recommendation model in dynamically modeling user preferences and balancing accuracy and non-accuracy aspects. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An optimized Fuzzy PI control method utilizing an improved QPSO for the hydrogen supply of PEMFC 18

An optimized Fuzzy PI control method utilizing an improved Q...

引用

18th IEEE Conference on Industrial Electronics and Applications, ICIEA 2023

作者： Xue, Haoyuan Zhang, Hailun Sun, Wenxu Yao, Ailing Jia, Lei Shandong University Institute of Marine Science and Technology Qingdao China Shandong University The School of Control Science and Engineering Jinan China

ISBN: (纸本)9798350312201

This paper proposes a Fuzzy logic PI control method for the hydrogen supply sub-system of the Proton Exchange Membrane Fuel Cell(PEMFC). The parameters of the controller are optimized using an improved Quantum-behaved Particle Swarm Optimization (QPSO) method. During the iterative optimization process with QPSO, the Logistic chaos mode is used to initialize the optimization algorithm by generating a set of random numbers as the initial population. The improved QPSO initialize method can effectively avoid the algorithm from getting stuck in local optima. The proposed control algorithm is based on a control-oriented model of the fuel cell, which established by combining the reaction process and the hydrogen supply and recirculation sub-system using the ejector. The hydrogen excess ratio and the ejector inlet pressure are controlled to the set value under load changes. The results indicate that the proposed control strategy has an improvement in regulation time and overshoot reduction of the hydrogen pressure and excess ratio compared with the traditional PID and fuzzy PI control strategies. © 2023 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Visual Positioning System of Bag Removal Robot Based on Deep Learning 9

Visual Positioning System of Bag Removal Robot Based on Deep...

引用

9th International Conference on Intelligent Computing and Signal Processing, ICSP 2024

作者： Liu, Bo Tang, Ruiyin College of electrical engineering North China University of Science and Technology Tangshan China School of electronic and control engineering North China Institute of Aerospace Engineering Langfang065000 China

ISBN: (纸本)9798350376548

In industrial production, the dumping of raw material packaging is mostly done manually, which not only affects production efficiency but also endangers the health of workers. This article proposes an improved algorithm based on YOLOV5, which uses Mobiletv3 instead of the YOLOV5 backbone network, adjusts parameters using an improved SE attention mechanism, and optimizes the model using the LeakyReLU activation function. The entire system uses an improved algorithm to detect the target bag rope, uses a depth camera to obtain the target coordinates, and finally calculates the target coordinates in the robot coordinate system. Compared with Fast RCNN and YOLOV5 algorithms, the improved YOLOV5 MobileNetV3 algorithm has a knot detection accuracy of 97.5%, a recall rate of 92.43%, and an F1 score of 94.8. The model has a small volume, fast detection speed, and a single image detection time of only 187ms, with a mapping rate of 97.5%. The error between the coordinates obtained after hand eye calibration and the actual coordinates of the robotic arm in the XYZ axis direction does not exceed 3mm, and the actual coordinates are much smaller than the target size. © 2024 IEEE.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Dynamic System Based on SAE-LDS Model for Fault Diagnosis 13

Nonlinear Dynamic System Based on SAE-LDS Model for Fault Di...

引用

13th IEEE Data Driven control and Learning Systems Conference, DDCLS 2024

作者： Tang, Xiaochu Zhang, Yi Zhang, Xinmin Song, Zhihuan School of Automation Shenyang Aerospace University Liaoning Province Shenyang110136 China College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Zhejiang Province Hangzhou310027 China

ISBN: (纸本)9798350361674

Dynamic, uncertainty and nonlinearity are three very important characteristics of complex industrial process data. In this paper, a method of fault detection and classification based on stacked autoencoder-linear dynamic system (SAE-LDS) model is proposed. This method aims to simultaneously consider multiple characteristics of industrial process data for fault detection and classification. Firstly, the deep learning algorithm SAE is used to mine the nonlinear characteristic of process data. On this basis, the SAE model is embedded into the LDS model. The LDS model is used to further extract the dynamics and uncertainty, so as to establish a SAE-LDS model that can comprehensively consider multiple characteristics of data. Finally, the SAE-LDS model is applied to the TE process, compared with the traditional method for fault detection and fault classification. The experimental results show that SAE- LDS model has good effectiveness. © 2024 IEEE.

关键词： data-driven fault classification fault detection linear dynamic system stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Tunnel crack detection method based on Crack-Aware Vision Transformer

引用

Journal of Traffic and Transportation engineering(English Edition) 2025年

作者： Xuanran Liu Liqiang Zhu Yaodong Wang Zujun Yu School of Mechanical， Electronic and Control Engineering， Beijing Jiaotong University Frontiers Science Center for Smart High-speed Railway System， Beijing Jiaotong University

The occurrence of cracks as a common surface defect in tunnel linings is influenced by a combination of internal and external factors. In recent years， computer vision methods have been widely applied in the field of crack detection. Deep learning has the capability to handle large-scale crack image data and automatically extract crack features. However， owing to numerous difficulties， including low-quality images， intricate cracks， and complex background environments， it is challenging to solve these tricky issues in tunnel crack detection. Therefore， this paper proposes a tunnel lining crack detection model based on Crack-aware Vision Transformer (CAViT)， which includes a perceptual vision transformer backbone network and an improved decoding network. The vision Transformer model has a stronger contextual modeling ability and is suitable for the task of extracting features from tunnel cracks with long， fine， and irregular characteristics. Due to the limitations of the attention mechanism based on a fixed window in modeling long-range relationships， we propose Crack-aware self-attention with the ability to increase the attention to relevant features and extract long-distance feature dependencies. This attention mechanism focuses on the crack area by learning the transformation parameters of the sampled window and reference points from the prediction module， and the position bias generated by the transformation compensate in the position encoding. Subsequently， we employ recurrent convolution layers to enhance the fusion network's ability to integrate contextual information. Our proposed CAViT is evaluated on the Crack500 dataset and a self-made tunnel crack dataset. Experimental results show that our network achieves the highest scores in terms of crack intersection-over-union (IoU) and accuracy (Acc) compared to other transformer models in both datasets. These results demonstrate the suitability of our CAViT for pavement crack and tunnel crack detection tasks， sho

关键词：

来源：评论

学校读者我要写书评

暂无评论

GRU combined model based on multi-objective optimization for short-term residential load forecasting

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 10423-10440页

作者： Yi, Lingzhi Peng, Xinlong Fan, Chaodong Wang, Yahui Li, Yunfan Liu, Jiangyong College of Automation and Electronic Engineering Xiangtan University Hunan Engineering Research Center of Multi-energy Cooperative Control Technology Hunan Xiangtan China School of Computer Science and Technology Hainan University Hainan China College of Electrical and Information Engineering Hunan University Changsha China

Reliable and accurate short-term forecasting of residential load plays an important role in DSM. However, the high uncertainty inherent in single-user loads makes them difficult to forecast accurately. Various traditional methods have been used to address the problem of residential load forecasting. A single load forecast model in the traditional method does not allow for comprehensive learning of data characteristics for residential loads, and utilizing RNNs faces the problem of long-term memory with vanishing or exploding gradients in backpropagation. Therefore, a gated GRU combined model based on multi-objective optimization is proposed to improve the short-term residential load forecasting accuracy in this paper. In order to demonstrate the effectiveness, GRUCC-MOP is first experimentally tested with the unimproved model to verify the model performance and forecasting effectiveness. Secondly the method is evaluated experimentally with other excellent forecasting methods: models such as DBN, LSTM, GRU, EMD-DBN and EMD-MODBN. By comparing simulation experiments, the proposed GRU combined model can get better results in terms of MAPE on January, April, July, and November load data, so this proposed method has better performance than other research methods in short-term residential load forecasting. © 2024 - IOS Press. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Realization of a quadrupole topological insulator phase in a gyromagnetic photonic crystal

引用

National science Review 2024年第11期11卷 47-53页

作者： Peiheng Zhou Gui-Geng Liu Zihao Wang Shuwei Li Qindong Xie Yunpeng Zhang Subhaskar Mandal Xiang Xi Zhen Gao Longjiang Deng Baile Zhang National Engineering Research Center of Electromagnetic Radiation Control Materials Key Laboratory of Multi-spectral Absorbing Materials and Structures of Ministry of EducationUniversity of Electronic Science and Technology of China Division of Physics and Applied Physics School of Physical and Mathematical Sciences Nanyang Technological University School of Electrical Engineering and Intelligentization Dongguan University of Technology Department of Electronic and Electrical Engineering Southern University of Science and Technology Centre for Disruptive Photonic Technologies The Photonics InstituteNanyang Technological University

The field of topological photonics was initiated with the realization of a Chern insulator phase in a gyromagnetic photonic crystal(Ph C) with broken time-reversal symmetry(T), hosting chiral edge states that are topologically protected propagating modes. Along a separate line of research, a quadrupole topological insulator was the first higher-order topological phase supporting localized corner states, but has been so far limited to T-invariant systems, as T is a key ingredient in early models. Here we report the realization of a quadrupole topological insulator phase in a gyromagnetic Ph C, as a consequence of topological phase transition from the previously demonstrated Chern insulator phase. The phase transition has been demonstrated with microwave measurements, which characterize the evolution from propagating chiral edge states to localized corner states. We also demonstrate the migration of topological boundary states into the continuum, when the gyromagnetic Ph C is magnetically tuned. These results extend the quadrupole topological insulator phase into T-broken systems, and integrate topologically protected propagating and localized modes in a magnetically tunable photonic crystal platform.

关键词： quadrupole topological insulator time-reversal symmetry breaking corner states topological phase transition

来源：评论

学校读者我要写书评

暂无评论

Residual Carrying Capacity Evaluation and Parking Orbit Replanning for Lunar Exploration Launch Vehicle

引用

Advances in Astronautics science and Technology 2024年第1期7卷 65-78页

作者： Wang, Cong Wang, Jinbo Song, Zhengyu Beijing Aerospace Automatic Control Institute Beijing100854 China School of Systems Science and Engineering Sun Yat-Sen University Guangzhou510275 China China Academy of Launch Vehicle Technology Beijing100076 China

To cope with the potential thrust-drop malfunction of the manned lunar exploration launch vehicle, a parking orbit replanning method is proposed based on the evaluation of the residual carrying capacity of the launcher. By analyzing the constraints of the whole flight profile and the characteristics of the Earth–Moon transfer orbit systematically, the offline trajectory planning algorithm exhibits improved convergence performance, and thus can be used to evaluate the residual carrying capacity as thrust-drop happens. For the situations that the launcher is not capable of injecting the transfer orbit, a sequential orbit/trajectory replanning method is designed to guarantee the safety of the astronauts. On the premise of ensuring the altitude of the parking orbit, the elements about the orbital plane are further optimized to provide a favorable initial state for the subsequent rescue action. Meanwhile, the nonlinearity of the terminal constraints is alleviated by the injection point forecast, and the initial reference is generated by convex optimization method with well convergence;thus, the solving efficiency of the sequential replanning algorithm can be improved. Simulation results show the proposed method can generate the trajectory that transport the spacecraft to the optimal parking orbit under the thrust-drop malfunction situation. This is an English translated version of "Residual Carrying Capacity Evaluation and Parking Orbit Re-planning for Lunar Exploration Launch Vehicle". © Chinese Society of Astronautics 2024. corrected publication 2024.

关键词： Lunar missions

来源：评论

学校读者我要写书评

暂无评论

Multiple Four-way Shuttle Path Planning Problem in Shuttle-Based Storage and Retrieval Systems: An Improved Conflict-Based Search Algorithm 14

Multiple Four-way Shuttle Path Planning Problem in Shuttle-B...

引用

14th International Conference on Logistics and Systems engineering

作者： Wang, Yanyan Wang, Zefeng Wang, Xuemei Man, Rongjun Shenzhen Research Institute of Shandong University Guangdong Shenzhen518057 China School of Control Science and Engineering Shandong University Shandong Jinan250061 China

ISBN: (纸本)9798331314347

A unique automated warehousing system called the four-way shuttle system has gained popularity recently because of its high adaptability and capacity to function across aisles and tiers. The four-way shuttle can move in four directions along fixed guideways. Therefore, the conflict-free routing of multiple four-directional shuttles within the same layer becomes particularly significant. This study develops a mathematical model for optimizing conflict-free path planning for multiple four-way shuttles to minimize total task completion time. We introduce the Dynamic Potential Conflict-Based Search (DPCBS) algorithm to facilitate conflict-free navigation for four-way shuttles. DPCBS enhances the Conflict-Based Search (CBS) algorithm's high-level search strategy by integrating the Dynamic Potential Search algorithm and augments the low-level search strategy with the Safe Interval Path Planning algorithm. This algorithm also incorporates priority strategies to improve its efficacy. Experimental results show that DPCBS with the priority strategy significantly outperforms the original algorithm in computational efficiency and success rate, effectively generating conflict-free paths for the four-way shuttle system. © (2025) by Aussino Academic Publishing House All rights reserved.

关键词： Guideways

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Intelligent Decision-Making for Orbital Game of Satellite Swarm 29th

Deep Reinforcement Learning-Based Intelligent Decision-Makin...

引用

29th International Conference on Computational and Experimental engineering and sciences, ICCES 2023

作者： Yu, Weizhuo Yue, Xiaokui Huang, Panxing Liu, Chuang National Key Laboratory of Aerospace Flight Dynamics School of Astronautics Northwestern Polytechnical University Xi’an710072 China Science and Technology on Space Intelligent Control Laboratory Beijing Institute of Control Engineering Beijing100094 China

ISBN: (纸本)9783031429866

Recent years have witnessed the rapid development of aerospace science and technology, and the orbital game technology has shown great potential value in the field of failed satellite maintenance, debris removal, etc. In this case, orbital game is often characterized by nonlinear dynamic model, unknown state information, high randomness, but the existing approaches to deal with game problem are difficult to be applied. The analytical method based on game theory is only applicable to simple scenarios, and it is challenging to find the optimal strategy for such complex scenarios as satellite swarm game. It should be noted that deep reinforcement learning has some research basis in the cooperative decision-making and control of multi-agents. In view of its powerful perception and decision ability, this paper applies deep reinforcement learning to solve the orbital game problem of satellite swarm. Firstly, the game scenario is modeled, where typical constraints, e.g., minimum time, optimal fuel, and collision avoidance, are taken into consideration in the game process, and then the multi-agent reinforcement learning algorithm is developed to solve the optimal maneuver strategy. The algorithm is based on the Actor-Critic architecture and uses a centralized training and decentralized execution approach to solve the optimal joint maneuver strategy. For different task scenarios, the action space, state observation space, and reward space are designed to introduce more rewards that match the specific game tasks to make the algorithm converge quickly, so that the satellite swarm emerges and executes better intelligent strategies to complete the corresponding game task. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Game theory

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：