检索结果-内蒙古大学图书馆

Multi-scale feature fused stacked autoencoder and its application for soft sensor modeling

Chinese Journal of Chemical Engineering 2025年 81卷 241-254页

作者： Li, Zhi Xia, Yuchong Long, Jian Liu, Chensheng Zhang, Longfei State Key Laboratory of Industrial Control Technology East China University of Science and Technology Shanghai 200237 China Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education East China University of Science and Technology Shanghai200237 China Huzhou Institute of Industrial Control Technology Huzhou313099 China Engineering Research Center of Process System Engineering Ministry of Education East China University of Science and Technology Shanghai200237 China

Deep Learning has been widely used to model soft sensors in modern industrial processes with nonlinear variables and uncertainty. Due to the outstanding ability for high-level feature extraction, stacked autoencoder (SAE) has been widely used to improve the model accuracy of soft sensors. However, with the increase of network layers, SAE may encounter serious information loss issues, which affect the modeling performance of soft sensors. Besides, there are typically very few labeled samples in the data set, which brings challenges to traditional neural networks to solve. In this paper, a multi-scale feature fused stacked autoencoder (MFF-SAE) is suggested for feature representation related to hierarchical output, where stacked autoencoder, mutual information (MI) and multi-scale feature fusion (MFF) strategies are integrated. Based on correlation analysis between output and input variables, critical hidden variables are extracted from the original variables in each autoencoder's input layer, which are correspondingly given varying weights. Besides, an integration strategy based on multi-scale feature fusion is adopted to mitigate the impact of information loss with the deepening of the network layers. Then, the MFF-SAE method is designed and stacked to form deep networks. Two practical industrial processes are utilized to evaluate the performance of MFF-SAE. Results from simulations indicate that in comparison to other cutting-edge techniques, the proposed method may considerably enhance the accuracy of soft sensor modeling, where the suggested method reduces the root mean square error (RMSE) by 71.8%, 17.1% and 64.7%, 15.1%, respectively. © 2025 Chemical Industry and Engineering Society of China, and Chemical Industry Press Co., Ltd.

关键词： Frequency estimation

来源：评论

学校读者我要写书评

暂无评论

A novel macroscopic traffic model based on generalized optimal velocity model

引用

Chinese Physics B 2011年第1期20卷 419-425页

作者：周玄昊吕勇哉 State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and ControlZhejiang University

In this paper, we adopt the coarse graining method proposed by Lee H K et al. to develop a macroscopic model from the microscopic traffic model-GOVM. The proposed model inherits the parameter p which considers the influence of next-nearest car introduced in the GOVM model. The simulation results show that the new model is strictly consistent with the former microscopic model. Using this macroscopic model, we can avoid considering the details of each traffic on the road, and build more complex models such as road network model easily in the future.

关键词： macroscopic model microscopic model traffic flow

来源：评论

学校读者我要写书评

暂无评论

Node-Dynamically Scalable Distributed Time Reversal Wireless Power Transfer System Based on Adaptive Phase Alignment

引用

IEEE Antennas and Wireless Propagation Letters 2025年

作者： Ao, Xiaochen Liang, Mu-Sheng Li, Shuyu Wang, Yinchen Wang, Bing-Zhong Wang, Ren University of Electronic Science and Technology of China Institute of Applied Physics Chengdu611731 China Huzhou Institute of Zhejiang University Huzhou313000 China Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China

To enable efficient and precise wireless power transfer in large-scale, dynamic wireless sensor networks (WSNs), a distributed time reversal wireless power transfer (DTR-WPT) system is designed. Using power equalization, frequency synchronization, and time reversal (TR) technology, the system achieves robust phase alignment and coherent energy focusing at the target, adaptable to node changes and spatial distribution. With time reversal mirror (TRM) units for phase detection and compensation, the system maintains precise alignment across configurations, enhancing scalability and efficiency for flexible, distributed applications in complex environments. © 2002-2011 IEEE.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

Design and development of a new autonomous transportation robot for finished vehicles docking transportation in RO/RO logistics terminal

引用

Advanced Engineering Informatics 2025年 66卷

作者： Xu, Yongkang Zhang, Lin Liu, Zhi Wang, Shoukun Wang, Junzheng State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing 100081 China

With the continuous growth of the automobile trade, the inefficiency of traditional cargo transshipment in Roll-On/Roll-Off (RO/RO) terminals has become increasingly pronounced. As a result, the adoption of autonomous transportation robot (ATR) for the automatic handling of finished vehicles has seen significant growth. However, ATRs designed for this purpose face several limitations, including suboptimal mobility performance and the necessity for additional infrastructure to support their operation. This paper introduces a novel ATR that offers enhanced flexibility and operational capability. To further optimize the positioning of LiDAR, we develop a multi-stage LiDAR fusion algorithm for the precise localization of finished vehicles, incorporating an event-triggered decision-making approach to improve positioning accuracy. Based on the accurate positioning data, we propose a docking strategy consisting of two key phases: the approach phase and the docking phase. During the docking phase, an enhanced Model Predictive control (MPC) algorithm, integrated with a Radial Basis Function (RBF) neural network, is designed to enable real-time adjustment of the robot's docking attitude. The effectiveness of the proposed approach is validated through real-world robot experimentals demonstrating its practical viability. © 2025

关键词： Docking control Finished vehicles RO/RO terminal Transportation robot

来源：评论

学校读者我要写书评

暂无评论

UGNA-VPR: A Novel Training Paradigm for Visual Place Recognition Based on Uncertainty-Guided NeRF Augmentation

arXiv

引用

arXiv 2025年

作者： Shen, Yehui Zhang, Lei Li, Qingqiu Zhao, Xiongwei Wang, Yue Lu, Huimin Chen, Xieyuanli College of Intelligence Science and Technology National University of Defense Technology China Faculty of Robot Science and Engineering Northeastern University China School of Electronic and Information Engineering Harbin Institute of Technology Shenzhen China State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University China SIASUN Robot& Automation Co. Ltd China School of Computer Science Fudan University China

Visual place recognition (VPR) is crucial for robots to identify previously visited locations, playing an important role in autonomous navigation in both indoor and outdoor environments. However, most existing VPR datasets are limited to single-viewpoint scenarios, leading to reduced recognition accuracy, particularly in multi-directional driving or feature-sparse scenes. Moreover, obtaining additional data to mitigate these limitations is often expensive. This paper introduces a novel training paradigm to improve the performance of existing VPR networks by enhancing multi-view diversity within current datasets through uncertainty estimation and NeRF-based data augmentation. Specifically, we initially train NeRF using the existing VPR dataset. Then, our devised self-supervised uncertainty estimation network identifies places with high uncertainty. The poses of these uncertain places are input into NeRF to generate new synthetic observations for further training of VPR networks. Additionally, we propose an improved storage method for efficient organization of augmented and original training data. We conducted extensive experiments on three datasets and tested three different VPR backbone networks. The results demonstrate that our proposed training paradigm significantly improves VPR performance by fully utilizing existing data, outperforming other training approaches. We further validated the effectiveness of our approach on self-recorded indoor and outdoor datasets, consistently demonstrating superior results. Our dataset and code have been released at https://***/nubot-nudt/UGNA-VPR. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Trajectory Generation Based on Traversable Planes in 3D Complex Architectural Spaces

arXiv

引用

arXiv 2025年

作者： Zhang, Mengke Tian, Zhihao Xia, Yaoguang Xu, Chao Gao, Fei Cao, Yanjun The State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou310027 China Huzhou Institute Zhejiang University Huzhou Key Laboratory of Autonomous System Huzhou313000 China China Tobacco Zhejiang Industrial Co. Ltd. Hangzhou310024 China

With the increasing integration of robots into human life, their role in architectural spaces where people spend most of their time has become more prominent. While motion capabilities and accurate localization for automated robots have rapidly developed, the challenge remains to generate efficient, smooth, comprehensive, and high-quality trajectories in these areas. In this paper, we propose a novel efficient planner for ground robots to autonomously navigate in large complex multi-layered architectural spaces. Considering that traversable regions typically include ground, slopes, and stairs, which are planar or nearly planar structures, we simplify the problem to navigation within and between complex intersecting planes. We first extract traversable planes from 3D point clouds through segmenting, merging, classifying, and connecting to build a plane-graph, which is lightweight but fully represents the traversable regions. We then build a trajectory optimization based on motion state trajectory and fully consider special constraints when crossing multi-layer planes to maximize the robot’s maneuverability. We conduct experiments in simulated environments and test on a CubeTrack robot in real-world scenarios, validating the method’s effectiveness and practicality. Copyright © 2025, The Authors. All rights reserved.

关键词： Flight paths

来源：评论

学校读者我要写书评

暂无评论

Boolean matrix compressed sensing

Boolean matrix compressed sensing

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Qiang Liu Mahdi Soleymani Hessam Mahdavifar National Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China Halıcıoğlu Data Science Institute University of California San Diego La Jolla CA USA Department of Electrical and Computer Engineering Northeastern University Boston MA USA

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In real-world datasets, leveraging the low-rank and sparsity properties enables developing efficient algorithms across a diverse array of data-related tasks, including compression, compressed sensing, matrix completion, etc. Notably, these two properties often coexist in certain real-world datasets, especially in Boolean datasets and quantized real-valued datasets. To harness the advantages of low-rank and sparsity simultaneously, we adopt a technique inspired by compressed sensing and Boolean matrix completion. Our approach entails compressing a low-rank sparse Boolean matrix by performing inner product operations with a randomly generated Boolean matrix. We then propose a decoding algorithms based on message-passing techniques to recover the original matrix. Our experiments demonstrate superior recovery performance of our proposed algorithms compared to Boolean matrix completion, with equal measurement requirements.

关键词： Image coding Signal processing algorithms Signal processing Acoustics Sensors Decoding Sparse matrices Speech processing Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Doppler Shift-Compensated FMCW Algorithm for Centimeter-Level Acoustic Single-Anchor Positioning of Moving Targets in Narrow Spaces.

引用

IEEE Sensors Journal 2025年第11期25卷 20195-20208页

作者： Cui, Weimeng Xi, Yuzhang Liu, Guangyao Jia, Naizheng Hu, Peixuan Li, Shuyu Wang, Zhi Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China Zhejiang University Huzhou Institute Huzhou313000 China

This paper proposes a novel Doppler shift-compensated Frequency Modulated Continuous Wave (DSC-FMCW) algorithm for achieving high-precision Time of Arrival (TOA) estimation of moving targets based on acoustics. In this algorithm, the stationary speaker transmits a mixed signal with upchirp and downchirp components, received by the moving microphone. Measurements are then compensated using the DSC-FMCW method. We then apply this algorithm to achieve two-dimensional positioning of moving targets in narrow spaces, using only one external speaker. In this method, a mirror-image speaker concept is introduced, where the primary reflection from the opposite wall is treated as coming from the mirror-image speaker, while reflections from the floor and ceiling are excluded as multipath signals. Additionally, considering the inability to synchronize the microphone and speaker, we leverage the characteristics of narrow spaces and the Doppler effect to achieve precise clock synchronization by estimating the absolute distance from a reference position to the speaker. Experiments show that the DSC-FMCW algorithm outperforms existing methods, achieving high accuracy in both open and multipath-affected scenarios at a target speed of 1.5 m/s, with mean errors of 0.0219 m and 0.0418 m, respectively. Additionally, experiments in a 1.735 m × 6.5 m corridor demonstrate an average error of 0.0446 m and a 95th percentile error of 0.0872 m. The proposed algorithm shows strong accuracy and robustness. © 2001-2012 IEEE.

关键词： Doppler effect

来源：评论

学校读者我要写书评

暂无评论

Map building for dynamic environments using grid vectors

引用

Journal of Zhejiang University-Science C(Computers and Electronics) 2011年第7期12卷 574-588页

作者： Wen-fei WANG,Rong XIONG ,Jian CHU (state key laboratory of industrial control technology,institute of cyber-systems and control,Zhejiang University,Hangzhou 310027,China) State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University

This paper addresses the problem of creating a geometric map with a mobile robot in a dynamic indoor *** form an accurate model of the environment,we present a novel map representation called the 'grid vector',which combines each vector that represents a directed line segment with a slender occupancy grid map.A modified expectation maximization (EM) based approach is proposed to evaluate the dynamic objects and simultaneously estimate the robot path and the map of the *** probability of each grid vector is evaluated in the expectation step and then used to distinguish the vector into static and dynamic *** robot path and map are estimated in the maximization step with a graph-based simultaneous localization and mapping (SLAM) *** representation we introduce provides advantages on making the SLAM method strictly statistic,reducing memory cost,identifying the dynamic objects,and improving the accuracy of the data *** SLAM algorithm we present is efficient in computation and *** on three different kinds of data sets show that our representation and algorithm can generate an accurate static map in a dynamic indoor environment.

关键词： Grid vector Line Segments Dynamic Simultaneous localization and mapping (SLAM) Expectation maximization (EM)

来源：评论

学校读者我要写书评

暂无评论

Distributed event-triggered adaptive control for second-order nonlinear uncertain multi-agent systems

引用

Chinese Journal of Aeronautics 2021年第10期34卷 237-247页

作者： Ming XIAO Zhitao LIU Hongye SU The State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and ControlZhejiang UniversityHangzhou 310027China

In this paper,the event-triggered consensus control problem for nonlinear uncertain multi-agent systems subject to unknown parameters and external disturbances is *** dynamics of subsystems are second-order with similar structures,and the nodes are connected by undirected *** event-triggered mechanisms are not only utilized in the transmission of information from the controllers to the actuators,and from the sensors to the controllers within each agent,but also in the communication between *** on the adaptive backstepping method,extra estimators are introduced to handle the unknown parameters,and the measurement errors that occur during the event-triggered communication are well handled by designing compensating terms for the control *** presented distributed event-triggered adaptive control laws can guarantee the boundness of the consensus tracking errors and the Zeno behavior is ***,the update frequency of the controllers and the load of communication burden are vastly *** obtained control protocol is further applied to a multi-input multi-output second-order nonlinear multi-agent system,and the simulation results show the effectiveness and advantages of our proposed method.

关键词： Adaptive distributed control structure Event-triggered control Multi-agent systems Second-order nonlinear models

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：