检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Qu, Wentao Shao, Yuantian Meng, Lingwu Huang, Xiaoshui Xiao, Liang Nanjing University of Science and Technology China Shanghai AI Laboratory China

Point cloud upsampling (PCU) enriches the representation of raw point clouds, significantly improving the performance in downstream tasks such as classification and reconstruction. Most of the existing point cloud upsampling methods focus on sparse point cloud feature extraction and upsampling module design. In a different way, we dive deeper into directly modelling the gradient of data distribution from dense point clouds. In this paper, we proposed a conditional denoising diffusion probability model (DDPM) for point cloud upsampling, called PUDM. Specifically, PUDM treats the sparse point cloud as a condition, and iteratively learns the transformation relationship between the dense point cloud and the noise. Simultaneously, PUDM aligns with a dual mapping paradigm to further improve the discernment of point features. In this context, PUDM enables learning complex geometry details in the ground truth through the dominant features, while avoiding an additional upsampling module design. Furthermore, to generate high-quality arbitrary-scale point clouds during inference, PUDM exploits the prior knowledge of the scale between sparse point clouds and dense point clouds during training by parameterizing a rate factor. Moreover, PUDM exhibits strong noise robustness in experimental results. In the quantitative and qualitative evaluations on PU1K and PUGAN, PUDM significantly outperformed existing methods in terms of Chamfer Distance (CD) and Hausdorff Distance (HD), achieving state of the art (SOTA) performance. Copyright © 2023, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Maximum Entropy Inverse Reinforcement Learning Based on Frenet Frame Sampling for Human-Like Autonomous Driving

Maximum Entropy Inverse Reinforcement Learning Based on Fren...

引用

International Conference on Intelligent Transportation

作者： Tangyike Zhang Shuo Sun Jiamin Shi Shitao Chen Marcelo H. Ang Jingmin Xin Nanning Zheng National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Shaanxi China Department of Mechanical Engineering National University of Singapore Singapore

Ensuring social acceptability is a key factor in the successful operation of autonomous vehicles. To achieve this, it is important to extract driving habits from expert human drivers. This paper proposes a method for training reward functions using maximum entropy inverse reinforcement learning based on Frenet frame sampling. The proposed method is applied to learn reward functions for the replication of human driver's lane-changing and velocity-keeping behaviors in multi-lane scenarios from human driving dataset, outperforming traditional methods based on Cartesian frame sampling. Converting the reward value of each sample into a probability distribution in the sample space allows for the provision of a convex space with human driving characteristics to the lower-level trajectory planner. These enhancements will help autonomous vehicles to select trajectories that align more with human driving habits. Experimental results show that the learned reward function can characterize human drivers' tendencies in multi-lane scenarios across multiple optimization metrics and exhibit strong interpretability. The proposed method effectively extract human driving behavior and habits under test conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Universal Coil Structure Design Method with Accurate Numerical Computation in Wireless Power Transfer systems

A Universal Coil Structure Design Method with Accurate Numer...

引用

IEEE Energy Conversion Congress and Exposition, ECCE

作者： Yue Wu Yongbin Jiang Yaohua Li Zhou He Chang Wang Ziheng Xiao Xiaohua Wang Yi Tang School of Electrical Engineering State Key Laboratory of EIPE Xi’an Jiaotong University Xi’an China School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore School of Electrical and Electronic Engineering Huazhong University of Sci. and Tech. Wuhan China Department of Electrical and Photonics Engineering Technical University of Denmark Denmark

Conventional design and optimization methods for resonant coils in wireless power transfer systems (WPTSs) heavily rely on finite element simulations, which are very time-consuming and complex. In this paper, a novel Universal Coil Structure Design (UCSD) method is proposed to accelerate and optimize the design process of rounded rectangular coils in WPTSs. First, the analytical model of the resonant coil’s self-inductance is derived when no ferrite plate is added. Second, the image current method is adopted to calculate coil’s self-inductance when ferrite plates are added. Accurate numerical calculation methods are used for the derived analytical model to calculate the coil’s self-inductance quickly and precisely. Next, the working principle of the UCSD method is presented. The UCSD method can calculate the self-inductances of rectangular coils with the proposed analytical model and pinpoint the most possible range of optimal coil structure according to the given requirements from different WPTSs. Subsequently, the proposed UCSD method is applied to determine the optimal coil structures for two case studies with much less time consumption. Finally, a 1.5-kW WPT system prototype is built to verify the effectiveness of the proposed UCSD method. With the coupling coefficient k = 0.2, the maximum transfer efficiency reaches 95.57% and 94.91% for Case I and Case II while k = 0.15, the maximum transfer efficiency reaches 96.07% and 95.37% for Case I and Case II.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fully Distributed optimization for Combined Heat and Power Dispatch

Fully Distributed Optimization for Combined Heat and Power D...

引用

2022 IEEE Power and Energy Society General Meeting, PESGM 2022

作者： Yu, Peng Wan, Can Song, Yonghua College of Electrical Engineering Zhejiang University Hangzhou China State Key Laboratory of Internet of Things for Smart City University of Macau China

ISBN: (数字)9781665408233

ISBN: (纸本)9781665408233

Combined heat and power dispatch (CHPD) effectively improves overall energy efficiency and operational flexibility in the integrated electricity and heating system (IEHS). However, the centralized optimization of CHPD may cause privacy infringement of different energy nodes that possess individual multi-energy resources and loads. This paper proposes a fully distributed optimization method of CHPD based on the alternating direction method of multipliers (ADMM), which promotes the optimal coordination among multi-agents in IEHS with high computational efficiency and respects agents' privacy. The nodes in IEHS are regarded as energy agents, while the energy networks connecting each agent fully model the heat transfer delay and the nonlinearity of power flow to ensure the accuracy of the CHPD results. According to ADMM, the auxiliary observation variables of adjacent agents are formulated to decompose the entire CHPD problem into many subproblems, which are solved by each energy agent in parallel iteratively. The closed-form solution of each subproblem is deduced to extremely accelerate the computation speed of distributed optimization. Case studies based on a test IEHS validate the effectiveness of the proposed method. © 2022 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Silicon Content Control for Blast Furnace: Model-free DDQN-ICM Method

Silicon Content Control for Blast Furnace: Model-free DDQN-I...

引用

Chinese Automation Congress (CAC)

作者： Baocong Zhang Xuda Ding Wei Liu Cailian Chen Xinping Guan Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai P.R. China

Silicon content control is critical to ensure the quality of molten iron and the stable operation of the blast furnace. The complex reactions and large uncertainty of the blast furnace make it hard to control. Several predictive control-based methods were already studied in Silicon content control. However, the requirements of prediction model design and short predictive horizon limit the generalization and long-term optimization of the methods. To tackle these issues, we propose a deep double Q-learning (DDQN) and intrinsic curiosity module (ICM) based Silicon content control method. First, the deep Q-learning framework employed in our approach eliminates the need for a prediction model and supports long-range simulations, thereby enhancing algorithm generalization and long-term optimization capabilities. Second, DDQN and ICM help to avoid the over-optimistic of action taking and improve exploration efficiency to tackle the large uncertainty of the blast furnace. Third, to ensure operational safety, we have designed a regulation strategy that incorporates ε-greedy exploration and ICM, mitigating the risks posed by exploration actions. Finally, we validate the effectiveness of our method using on-site data, demonstrating that DDQN-ICM achieves superior performance in terms of tracking accuracy and disturbance rejection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel GNN-Based Node Importance Ranking Method in a Heterogeneous Network 7th

A Novel GNN-Based Node Importance Ranking Method in a Hete...

引用

7th Chinese Conference on Swarm Intelligence and Cooperative Control, CCSICC 2023

作者： Li, Shuyu Ji, Dedong Wang, Jingwei Xia, Weiguo Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian China Shenyang Aircraft Design and Research Institute Shenyang China

ISBN: (纸本)9789819733231

In a heterogeneous network, a reliable importance ranking of nodes can provide a useful reference for decision-making. Nevertheless, existing node importance ranking methods may not effectively integrate the characteristics of the edges and nodes in the graph, as well as the structural information. In this paper, a novel graph neural network-based heterogeneous network node importance ranking (GNN-HNNIR) method is proposed to rank the importance of different functional nodes in a heterogeneous network. GNN-HNNIR can adjust the node importance score based on those of neighboring nodes, which employ a multi-head attention mechanism to aggregate scores by pooling information from edges, nodes, and the graph structure. Finally, numerical experiments show that GNN-HNNIR can effectively evaluate the importance scores of different nodes with given small amount of data for training. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

STGCNFormer: Spatio-Temporal Dual-Stream Graph Convolutional Networks and Transformers for Traffic Forecasting

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Yang, Changzhi Pan, Huihui Wang, Jue Harbin Institute of Technology Research Institute of Intelligent Control and Systems Harbin150001 China Tongji University National Key Laboratory of Autonomous Intelligent Unmanned Systems Shanghai201210 China Ningbo Institute of Intelligent Equipment Technology Company Ltd. Ningbo315200 China University of Science and Technology of China Department of Automation Hefei230027 China

In intelligent transportation systems, traffic prediction constitutes the fundamental component of traffic optimization, aiming to precisely forecast traffic flow. Modeling spatio-temporal interactions is a crucial step in achieving long-term and accurate predictions. Traditional methods are mostly based on single-stream networks, which alternately extract spatio-temporal features through sequential iterations. However, time and space are inherently two different modalities. Employing a single-stream network to address multi-modal tasks is suboptimal. In this paper, we propose Spatio-Temporal Dual-Stream Graph Convolutional Networks and Transformers (STGCNFormer), a dual-stream network for traffic forecasting, decoupling spatio-temporal features in parallel through a temporal stream and a spatial stream. The core of STGCNFormer is a STGCNFormer block, comprising three components. The first component is a GCN block, which restricts the kernel of graph convolution and adopts Chebyshev polynomials of the first kind to approximate the convolutional kernel, capturing spatial interactions and achieving localized convolution. Secondly, we present a Transformer block, designed as a simplified version of vanilla Transformers, which captures temporal interactions and significantly reduces computational complexity. Thirdly, we propose a cross attention mechanism, consisting of a temporal attention mechanism and a spatial attention mechanism, which serves as a bidirectional bridge for sharing information between the dual streams. Experimental results demonstrate that STGCNFormer achieves superior prediction accuracy with reduced computational complexity compared with previous state-of-the-art methods. © 1967-2012 IEEE.

关键词： Air traffic control

来源：评论

学校读者我要写书评

暂无评论

Intelligent Fault Diagnosis of Rolling Bearing Based on Parameter Optimized VMD and Dense-1DCNN with Position-Encoded Temporal Attention

引用

Journal of Vibration Engineering & Technologies 2025年第6期13卷 1-22页

作者： Gao, Xuejin Zhao, Yumeng Han, Huayun Gao, Huihui Qi, Yongsheng Faculty of Information Technology Engineering Research Centre of Digital Community Ministry of Education Beijing Laboratory for Urban Mass Transit Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing China School of Electric Power Inner Mongolia University of Technology Hohhot China

Rolling bearing is the key component of rotating mechanical equipment, whose performance will affect the health and service life of the equipment significantly and directly. Therefore, the fault diagnosis of rolling bearing failures is necessary for avoiding the accidents caused by them. Because of their fault features being masked by noise, it is difficult to acquire the features and distinguish the types of faults by the nonlinear vibration signals of rolling bearing directly. To solve this problem, a fault diagnosis method for rolling bearings based on parameter optimized variational mode decomposition (VMD) and one-dimensional convolutional neural network (1DCNN) was proposed. Firstly, the whale optimization algorithm (WOA) improved by an adaptive convergence parameter and perturbation factors were applied to optimize the parameters of VMD. Secondly, the parameter optimized VMD was applied to obtain the required intrinsic mode functions (IMFs) from the vibration signals of rolling bearings to denoise them. Finally, densely connected 1DCNN model adding with the proposed position-encoded temporal attention module (PTAM), named PTAM-Dense-1DCNN, was used as the feature extraction and fault classification network for fault diagnosis. The result of the experiment performed on two experimental bearing datasets have shown the effectiveness of proposed methods, whose superiority over other representative methods has also been demonstrated by comparative experiments in this research.

关键词： Rolling bearing Fault diagnosis Parameter optimization Convolutional neural network Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Optimal experimental design: Formulations and computations

arXiv

引用

arXiv 2024年

作者： Huan, Xun Jagalur, Jayanth Marzouk, Youssef University of Michigan 1231 Beal Ave Ann ArborMI48109 United States Center for Applied Scientific Computing Lawrence Livermore National Laboratory 7000 East Ave LivermoreCA94550 United States Massachusetts Institute of Technology 77 Massachusetts Ave CambridgeMA02139 United States

Questions of ‘how best to acquire data’ are essential to modeling and prediction in the natural and social sciences, engineering applications, and beyond. Optimal experimental design (OED) formalizes these questions and creates computational methods to answer them. This article presents a systematic survey of modern OED, from its foundations in classical design theory to current research involving OED for complex models. We begin by reviewing criteria used to formulate an OED problem and thus to encode the goal of performing an experiment. We emphasize the flexibility of the Bayesian and decision-theoretic approach, which encompasses information-based criteria that are well-suited to nonlinear and non-Gaussian statistical models. We then discuss methods for estimating or bounding the values of these design criteria;this endeavor can be quite challenging due to strong nonlinearities, high parameter dimension, large per-sample costs, or settings where the model is implicit. A complementary set of computational issues involves optimization methods used to find a design;we discuss such methods in the discrete (combinatorial) setting of observation selection and in settings where an exact design can be continuously parameterized. Finally we present emerging methods for sequential OED that build non-myopic design policies, rather than explicit designs;these methods naturally adapt to the outcomes of past experiments in proposing new experiments, while seeking coordination among all experiments to be performed. Throughout, we highlight important open questions and challenges. © 2024, CC BY.

关键词： Design of experiments

来源：评论

学校读者我要写书评

暂无评论

Smoothing Gradient Tracking for Decentralized optimization over the Stiefel Manifold with Non-Smooth Regularizers

Smoothing Gradient Tracking for Decentralized Optimization o...

引用

IEEE Conference on Decision and Control

作者： Lei Wang Xin Liu State Key Laboratory of Scientific and Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China and University of Chinese Academy of Sciences Beijing China

Recently, decentralized optimization over the Stiefel manifold has attracted tremendous attentions due to its wide range of applications in various fields. Existing methods rely on the gradients to update variables, which are not applicable to the objective functions with non-smooth regularizers, such as sparse PCA. In this paper, to the best of our knowledge, we propose the first decentralized algorithm for non-smooth optimization over Stiefel manifolds. Our algorithm approximates the non-smooth part of objective function by its Moreau envelope, and then existing algorithms for smooth optimization can be deployed. We establish the convergence guarantee with the iteration complexity of $\mathcal{O}$ (∊ 4 ). Numerical experiments conducted under the decentralized setting demonstrate the effectiveness and efficiency of our algorithm.

关键词：

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：