检索结果-内蒙古大学图书馆

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

作者： Zhang, Rui Liu, Shan College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China

ISBN: (纸本)9798350361674

An improved path planning algorithm based on RRT∗ is proposed for the manipulator to generate a collision-free path for end-effector in this paper, which maximizes the manipulator's manipulability throughout the entire path. The algorithm introduces manipulability information as prior information to guide the RRT node toward desired regions. By introducing hybrid cost into improved RRT* algorithm, the path length is minimized while the expected manipulability is maximized. Finally, the end-effector path is transformed into a configuration trajectory by solving a multi-objective optimization problem. The simulation results compared with RRT* demonstrates the effectiveness of the proposed algorithm. © 2024 IEEE.

关键词： End effectors

来源：评论

学校读者我要写书评

暂无评论

Diversity and dynamic response of anaerobic ammonia oxidation granular sludge

引用

Journal of Environmental sciences 2025年第6期152卷 262-275页

作者： Jiahong Ye Xiang Li Yan Yuan Yayi Wang Yong Huang JunMa Han Wang Pengze Dang Pei-ling Xu School of Environmental Science and Engineering Suzhou University of Science and TechnologySuzhou 215009China State Key Laboratory of Pollution Control and Resources Reuse Shanghai Institute of Pollution Control and Ecological SecurityCollege of Environmental Science and EngineeringTongji UniversityShanghai 200092China State Key Laboratory of Urban Water Resource and Environment Harbin Institute of TechnologyHarbin 150090China

Red anaerobic ammonia oxidation (Anammox) granular sludge (AnGS) has been reported insuccessfully operating Anammox systems, and its color is associated with sludge ***, in long-term operating systems, AnGS exhibits different sensory colors, physicalstructures, community structures, and denitrification performance, but the relationship betweenthem has not yet been *** AnGS of the Anammox system, which has beenin operation for more than a decade, can be divided into twomain categories: red and *** specific Anammox activity (SAA) in conventional red AnGS increased continuously asthe particle size increased from <0.51 mm to 6.02 ± 0.84 mm. The SAA of white AnGS wereslightly lower than those of red AnGS with similarly-size granules but significantly higherthan AnGS with smaller red granules. Compared with red AnGS, the extracellular polymericsubstances of white AnGS were significantly reduced,mainly due to the higher intracellulariron content, resulting in lower heme c concentration. Thus, heme c may prove not to bean evaluative tool for measuring Anammox activity. Red and white AnGS, whether throughself-aggregation or adsorption by hydroxyl apatite and other carriers, will face the fate ofinternal voids during particle size growth. White AnGS exhibited amore complex microbialcommunity than red AnGS. Candidatus Brocadia was abundant in red AnGS and the abundanceincreased with increasing granule size. Candidatus Kuenenia and Candidatus Jetteniamade significant contributions to denitrification in white AnGS. This study provides a newperspective on particle selection for anammox engineering applications.

关键词： Anaerobic ammonium oxidation granular sludge Sensory diversity Intracellular iron Heme Enzyme activity Microbial diversity

来源：评论

学校读者我要写书评

暂无评论

TCPP: A Benchmark Platform for Traffic Congestion Prediction with Multi-source Auxiliary Data

TCPP: A Benchmark Platform for Traffic Congestion Prediction...

引用

2024 China Automation Congress, CAC 2024

作者： Zhou, Yusong Zhang, Xinmin Jiang, Xiaoyu Song, Zhihuan State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Zhejiang China Huzhou Institute of Industrial Control Technology Zhejiang Huzhou China

ISBN: (纸本)9798350368604

With rapid urbanization, traffic congestion has become a challenge to efficient urban transportation. To address this challenge, we develop a novel traffic congestion prediction platform (TCPP) which is a unified benchmark tool for traffic congestion prediction with multi-source auxiliary data. By combining data integration, model selection and evaluation modules, TCPP provides a standardized framework for researchers to compare and evaluate different models and datasets. Meanwhile, through a comprehensive and detailed configuration syntax, TCPP allows users to flexibly schedule tasks and execute multiple tasks continuously and uninterruptedly. In addition, two datasets collected from California highways are enriched with multi-source weather data and temporal features. We evaluate the performance of TCPP on these two datasets and demonstrate its effectiveness in predicting traffic congestion. The results demonstrate that TCPP can contribute to future research on traffic congestion prediction and the development of intelligent transportation systems and urban traffic management. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Few-shot object detection via class encoding and multi-target decoding

引用

IET Cyber-Systems and Robotics 2023年第2期5卷 1-14页

作者： Xueqiang Guo Hanqing Yang Mohan Wei Xiaotong Ye Yu Zhang State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhouChina Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province HangzhouChina

The task of few‐shot object detection is to classify and locate objects through a few annotated *** many studies have tried to solve this problem,the results are still not *** studies have found that the class margin significantly impacts the classification and representation of the targets to be *** methods use the loss function to balance the class margin,but the results show that the loss‐based methods only have a tiny improvement on the few‐shot object detection *** this study,the authors propose a class encoding method based on the transformer to balance the class margin,which can make the model pay more attention to the essential information of the features,thus increasing the recognition ability of the ***,the authors propose a multi‐target decoding method to aggregate RoI vectors generated from multi‐target images with multiple support vectors,which can significantly improve the detection ability of the detector for multi‐target *** on Pascal visual object classes(VOC)and Microsoft Common Objects in Context datasets show that our proposed Few‐Shot Object Detection via Class Encoding and Multi‐Target Decoding significantly improves upon baseline detectors(average accuracy improvement is up to 10.8%on VOC and 2.1%on COCO),achieving competitive *** general,we propose a new way to regulate the class margin between support set vectors and a way of feature aggregation for images containing multiple objects and achieve remarkable *** method is implemented on mmfewshot,and the code will be available later.

关键词： Class Margin Few-Shot Object Detection Multi-Target Transformer

来源：评论

学校读者我要写书评

暂无评论

Physically informed hierarchical learning based soft sensing for aero-engine health management unit

引用

Chinese Journal of Aeronautics 2025年第3期38卷 374-385页

作者： Aina WANG Pan QIN Yunbo YUAN Guang ZHAO Ximing SUN School of Control Science and Engineering Dalian University of TechnologyDalian 116024China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian 116024China School of Energy and Power Engineering Dalian University of TechnologyDalian 116024China

Partial Differential Equations(PDEs)are model candidates of soft sensing for aero-engine health management *** existing Physics-Informed Neural Networks(PINNs)have made ***,unmeasurable aero-engine driving sources lead to unknown PDE driving terms,which weaken PINNs *** this end,Physically Informed Hierarchical Learning followed by Recurrent-Prediction Term(PIHL-RPT)is ***,PIHL is proposed for learning nonhomogeneous PDE solutions,in which two networks NetU and NetG are *** is for learning solutions satisfying PDEs;NetG is for learning driving terms to regularize NetU ***,we propose a hierarchical learning strategy to optimize and couple NetU and NetG,which are integrated into a data-physics-hybrid loss ***,we prove PIHL-RPT can iteratively generate a series of networks converging to a function,which can approximate a solution to well-posed ***,RPT is proposed for prediction improvement of PIHL,in which network NetU-RP is constructed to compensate for information loss caused by data sampling and driving sources’***,artificial datasets and practical vibration process datasets from our wear experiment platform are used to verify the feasibility and effectiveness of PIHL-RPT based soft ***,comparisons with relevant methods,discussions,and PIHL-RPT based health monitoring example are given.

关键词： Hierarchical learning strategy Monitoring:Partial differen tial equations with unmeasurable driving terms Physically informed hierarchical learning followed by recurrent-prediction term Soft sensing

来源：评论

学校读者我要写书评

暂无评论

Toward a rapid and convenient nanoplastic quantification method in laboratory-scale study based on fluorescence intensity

引用

Frontiers of Environmental science & engineering 2024年第5期18卷 117-126页

作者： Ruiqi Yan Sen Lin Qian Ding Lei Zhang Xia Yu Wentao Zhao Qian Sui State Environmental Protection Key Laboratory of Environmental Risk Assessment and Control on Chemical Process School of Resources and Environmental EngineeringEast China University of Science and TechnologyShanghai200237China State Key Laboratory of Pollution Control and Resource Reuse College of Environmental Science and EngineeringTongji UniversityShanghai200092China Shanghai Institute of Pollution Control and Ecological Security Shanghai200092China

The thorough investigation of nanoplastics(NPs)in aqueous environments requires efficient and expeditious quantitative analytical methods that are sensitive to environmentally relevant NP concentrations and convenient to *** analysis-based quantitative methods have been acknowledged as effective and rapid approaches for quantifying NP concentrations in laboratory-scale ***,we compared three commonly used optical response indicators,namely fluorescence intensity(FI),ultraviolet absorbance,and turbidity,to assess their performance in quantifying ***,orthogonal experiments were conducted to evaluate the influence of various water quality parameters on the preferred indicator-based quantification *** results revealed that FI exhibits the highest correlation coefficient(>0.99)with NP ***,the limit of quantification(LOQ)for various types of NPs is exceptionally low,ranging from 0.0089 to 0.0584 mg/L in ultrapure water,well below environmentally relevant *** variations in water quality parameters such as pH,salinity,suspended solids(SS),and humic acid,a robust relationship between detectable FI and NP concentration was ***,an increased matrix,especially SS in water samples,results in an enhanced LOQ for ***,the quantitative method remains applicable in real water bodies,especially in drinking water,with NP LOQ as low as 0.0157–0.0711 mg/*** exceeds the previously reported detectable concentration for 100 nm NPs at 40µg/mL using surface-enhanced Raman *** study confirms the potential of FI as a reliable indicator for the rapid quantification of NPs in aqueous environments,offering substantial advantages in terms of both convenience and cost-effectiveness.

关键词： Nanoplastic quantification Fluorescence intensity Drinking water Limit of quantification(LOQ) Matrix effects

来源：评论

学校读者我要写书评

暂无评论

Variational Reconstruction and Simulation Experiments of Sea Surface Wind Field for Ocean Data Buoy

引用

Journal of Ocean University of China 2024年第3期23卷 577-582页

作者： LI Yunzhou HUANG Sixun YAN Shen SUN Xuejin QI Suiping WANG Zhongqiu TANG Xiaoyu College of Meteorology and Oceanography National University of Defense TechnologyChangsha 410073China Institute of Oceanographic Instrumentation Qilu University of Technology(Shandong Academy of Sciences)Qingdao 266061China State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhou 310027China Laoshan Laboratory Qingdao 266237China

The sea surface wind field is an important physical parameter in oceanography and *** the continuous refinement of numerical weather prediction,air-sea interface materials,energy exchange,and other studies,three-dimensional(3D)wind field distribution at local locations on the sea surface must be measured *** current in-situ observation of sea surface wind parameters is mainly achieved through the installation of wind sensors on ocean data ***,the results obtained from this single-point measurement method cannot reflect wind field distribution in a vertical direction above the sea ***,the present paper proposes a theoretical framework for the optimal inversion of the 3D wind field structure variation in the area where the buoy is *** variation analysis method is first used to reconstruct the wind field distribution at different heights of the buoy,after which theoretical analysis verification and numerical simulation experiments are *** results indicate that the use of variational methods to reconstruct 3D wind fields is significantly effective in eliminating disturbance errors in observations,which also verifies the correctness of the theoretical analysis of this *** findings of this article can provide a reference for the layout optimization design of wind measuring instruments in buoy observation systems and also provide theoretical guidance for the design of new observation buoys in the future.

关键词： moored buoy three-dimensional wind field distribution variational analysis wind field reconstruction

来源：评论

学校读者我要写书评

暂无评论

Experimental study on the influence of roadway shape on the evolution of outburst fluid static pressure

引用

International Journal of Coal science & technology 2024年第4期11卷 274-289页

作者： Jiang Xu Xiaomei Wang Liang Cheng Shoujian Peng Hailin Yang Bin Zhou Feng Jiao State Key Laboratory of Coal Mine Disaster Dynamics and Control Chongqing UniversityChongqing 400030China College of Safety Science and Engineering Xian University of Science and TechnologyXian 710054ShaanxiChina

To explore the static pressure dynamic disaster mechanism of coal-and-gas outburst(CGO)fluid,the self-developed multifield coupling large-scale physical simulation test system of coal mine dynamic disaster was used to carry out gas outburst and CGO physical simulation tests in straight,L-shaped and T-shaped *** influence of roadway shape on the evolution of static pressure was explored,and the role of pulverized coal in the process of static pressure dynamic disaster was *** results indicated that the static pressure showed a fluctuating downward trend during the outburst *** gas outburst,the middle and front parts of the roadway in the straight section roadway were the most serious areas of static pressure disasters in the three shapes of *** duration and range of high static pressure disaster in L-shaped roadway were larger than those in T-shaped and straight roadways in *** CGO,the most serious area of static pressure disaster in L-shaped and T-shaped roadways moved backward to the middle of the straight section roadway,and there was a rebound phenomenon in the process of static pressure fluctuation decline,which showed the pulse characteristics of *** the outburst,the static pressure dynamic disaster hazard of L-shaped roadway was higher than that of T-shaped roadway,and the static pressure at the bifurcation structure decayed faster than that at the turning structure,which indicated that T-shaped roadway was more conducive to the release of static pressure in roadway,thus reduced the risk of static pressure *** gas outburst,the static pressure attenuation of the fuid in the roadway before and after the turning and bifurcation structure was greater than that of *** peak static pressure and impulse of the fluid during gas outburst were 2 times and 4-5 times that of CGO *** presence of pulverized coal reduced the attenuation of static pressure and the hazard of dynamic disaster,prolonged

关键词： Gas outburst Coal-and-gas outburst.Static pressure Roadway shape Dynamic disaster.Outburst fluid

来源：评论

学校读者我要写书评

暂无评论

An Improved Multivariate state Estimation Technique for Condition Monitoring of Boiled Feedwater Pumps

An Improved Multivariate State Estimation Technique for Cond...

引用

2023 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes, SAFEPROCESS 2023

作者： Wu, Gaochao Que, Zijun Xu, Zhengguo Wu, Yixi Wang, Ziqi Zhejiang University State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Hangzhou China

ISBN: (纸本)9798350337754

Condition monitoring (CM) of boiled feedwater pumps (BFPs) is an important task for thermal power plants. Considering the variable operating conditions of BFPs, it is necessary to capture their dynamic features and update CM models in real time. In this paper, an improved multivariate state estimation technique (MSET) is proposed. Firstly, the states of BFPs are serialized to incorporate temporal features. Secondly, for the memory matrix (MM) of MSET, an expansion strategy is introduced, aiming to improve the generalization capability of the method. Finally, an MM thinning strategy is proposed to ensure the feasibility and improve the efficiency of the method. The experimental results show that state serialization and MM expansion greatly improve the accuracy and sensitivity of the method for CM of BFPs, and MM thinning avoids the method failure and improves the computational efficiency. © 2023 IEEE.

关键词： Feedwater pumps

来源：评论

学校读者我要写书评

暂无评论

Research on Traceability Method of Gas Leak for Emergency Auxiliary Support

Research on Traceability Method of Gas Leak for Emergency Au...

引用

2023 China Automation Congress, CAC 2023

作者： Cui, Tingting Dong, Huilin Zhou, Zhi Cao, Yuqi Hou, Dibo Zhang, Guangxin College of Control Science and Engineering State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China

ISBN: (纸本)9798350303759

In the field of environmental emergency, sudden gas leaks cause great harm to the economy and society. In recent years, gas leaks have occurred frequently, and the problem of locating the source of air pollution is mainly divided into two steps: dispersion and traceability. However, the application of mechanism modeling or data-driven modeling methods for dispersion prediction is difficult to meet computational efficiency and prediction accuracy. Conventional source estimation methods also have the disadvantage of local optima in tracing pollution sources. In this paper, we propose a gaussian-machine learning model for gas dispersion prediction using gaussian features as inputs, and the improved particle swarm optimization algorithm that takes into account globally search and optimization. Predicted concentration is utilized as the input of the traceability model. Results demonstrate that this method have better performance on estimating leak location and concentration. © 2023 IEEE.

关键词： Forecasting

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：