检索结果-内蒙古大学图书馆

14th International Conference on Environmental science and Development, ICESD 2023

作者： Zhao, Chunmei Chen, Bin School of Computer Science and Technology Harbin Institute of Technology Weihai264209 China

ISBN: (纸本)9783031560552

Total nitrogen (TN) in effluent of wastewater treatment plants is an important index to evaluate the effect of water treatment. Accurate prediction of effluent TN in the short term can provide data support for the optimized operation of wastewater treatment plants. In order to improve the prediction accuracy of effluent TN in sewage treatment process, this paper studied an effluent TN prediction model based on bidirectional recurrent neural network, which can capture more comprehensive context information by considering both past and future sequence information. The experimental results showed that compared with the coefficient of determination (R2) of RNN neural network on the test set was 0.423, the simulation and prediction accuracy of bidirectional recurrent neural network was higher, and the R2 of BiGRU was the highest (0.657). At the same time, adding attention mechanism to BiGRU could further improve the prediction accuracy, and the R2 was 0.671. In other recurrent neural networks, R2 from high to low is 2-GRU > BiLSTM > 2-LSTM > BiRNN > 2-RNN. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Soft-template synthesis of hierarchically porous structured polydimethylsiloxane toward flexible capacitive pressure sensor

引用

science China(Technological sciences) 2023年第9期66卷 2696-2706页

作者： HE ShiXue WU Jian DUAN YanHao SU BenLong LIU ShouYao TENG Fei WANG YouShan School of Mechatronics Engineering Harbin Institute of TechnologyHarbin 150001China National Key Laboratory of Science and Technology on Advanced Composites in Special Environments Harbin Institute of TechnologyHarbin 150090China Center for Rubber Composite Materials and Structures Harbin Institute of TechnologyWeihai 264209China

Flexible pressure sensors play an important role in the field of monitoring, owing to their inherent safety and the fact that they are embedded at the material level. Capacitive pressure sensors have been proven to be quite versatile, with the ability to change the sensitivity and monitoring range by modifying the pore structure of the dielectric layer(elastic modulus). In this paper, capacitive pressure sensors are devised, comprising hierarchical porous polydimethylsiloxane. Due to the inherent hollow and hierarchical micropore structure, the capacitive pressure sensor allows operation at a wider pressure range(~1000 kPa) while maintaining sensitivity(6.33 MPa-1) in the range of 0–300 k Pa. Subsequently, the capacitance output model of the sensor is optimized, which provides an overall approximation of the experimental values for the sensor performance. Additionally, the signal response of the“break up the whole into parts”(by analysis of the whole sensor in parts) is simulated and outputted by the finite element analysis. The simplified analysis model provides a good understanding of the relationship between the local pressure and the signal response of the pressure sensor. For practical applications, seal monitoring and rubber wheel pressure array system are tested, and the proposed sensor shows sufficient potential for application in large deformation elastomer products.

关键词： hierarchically porous structured flexible pressure sensor capacitive response mechanism hydrogel/silicone rubber emulsion

来源：评论

学校读者我要写书评

暂无评论

Enhancement of comprehensive properties of Nb-Si based in-situ composites by Ho rare earth doping

引用

Rare Metals 2024年第9期43卷 4508-4520页

作者： Wei Wei Qi Wang Rui-Run Chen Chao-Wen Zheng Yan-Qing Su National Key Laboratory for Precision Hot Processing of Metals School of Materials Science and EngineeringHarbin Institute of TechnologyHarbin 150001China

This study examines the microstructure,mechanical properties(with a focus on room-temperature toughness),and oxidation resistance of Ho-doped NbDSi based in-situ *** base alloy consists of the coarse primary Nb_(5)Si_(3)phase and the Nb_(5)Si_(3)+Nbss(Nb solid solution)eutectic *** doping influences the solidification *** the Ho doping is higher than0.2 at%,the alloys transform into eutectic *** can be solid-solved in trace amounts in the Nbss ***,most of Ho forms a stable Ho oxide phase,which alleviates oxygen contamination problem to some ***,the interface separation between Ho oxide and other phases reduces the plastic deformation ***,with 0.4 at%Ho doping,the K_(Q)value is18.03 MPa·m^(1/2),which is 31.1%higher than that of the base *** strength of the Ho-doped alloys does not deteriorate with an increase in ***,the large network-like Ho_(2)O_(3)in the 0.8Ho alloy causes a decrease in toughness and *** addition,the Ho oxide phase effectively blocks the inward oxygen *** 0.8 at%Ho doping,the oxidation mass gain per unit area is 10.16 mg·cm^(2),which is 39.7%lower than that of the base alloy.

关键词： Nb-Si based composites Rare earth elements Ho Microstructure Properties

来源：评论

学校读者我要写书评

暂无评论

Learning-based Variable Neighborhood Search Algorithm for Cloud Service Deployment Problem with Time Windows 22

Learning-based Variable Neighborhood Search Algorithm for Cl...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Meng, Fanchao Lu, Yang Lv, Weigong Chu, Dianhui Harbin Institute of Technology at Weihai School of Computer Science and Technology Weihai China

ISBN: (纸本)9798331509712

When services are deployed in a cloud environment, the selection of virtual machines mostly relies on the historical experience of service providers, which leads to a high cost of cloud resource. Additionally, such problem rarely considers the impact of service time on the cost of virtual machines. In this paper, we introduce and model the cloud service deployment problem with time windows (CSDPTW), wherein the cost of virtual machines is influenced by the usage time windows. To solve this problem, we propose a learning-based variable neighborhood search (L-VNS) algorithm. The algorithm first employs a hierarchical clustering algorithm to generate the initial solution. Then, a Q-learning-based reinforcement learning algorithm is used to optimize the selection of operators, which includes two neighborhood operators and three local search operators. To evaluate the performance of our proposed L-VNS, genetic algorithm (GA), variable neighborhood search (VNS), iterated local search (ILS) and the commercial solver CPLEX are applied to CSDPTW. Computational experiments on 20 test instances demonstrate that the proposed L-VNS algorithm can find better solutions than GA, VNS, ILS and CPLEX. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Breaking Solvation Dominance Effect Enabled by Ion-Dipole Interaction Toward Long-Spanlife Silicon Oxide Anodes in Lithium-Ion Batteries

引用

Nano-Micro Letters 2025年第4期17卷 367-380页

作者： Shengwei Dong Lingfeng Shi Shenglu Geng Yanbin Ning Cong Kang Yan Zhang Ziwei Liu Jiaming Zhu Zhuomin Qiang Lin Zhou Geping Yin Dalong Li Tiansheng Mu Shuaifeng Lou State Key Laboratory of Space Power-Sources School of Chemistry and Chemical EngineeringHarbin Institute of TechnologyHarbin 150001People’s Republic of China School of Marine Science and Technology Harbin Institute of Technology at WeihaiWeihai 264200People’s Republic of China Chongqing Research Institute of HIT Chongqing 401135People’s Republic of China

Micrometer-sized silicon oxide(SiO)anodes encounter challenges in large-scale applications due to significant volume expansion during the alloy/de-alloy ***,an innovative deep eutectic electrolyte derived from succinonitrile is introduced to enhance the cycling stability of SiO *** functional theory calculations validate a robust ion-dipole interaction between lithium ions(Li^(+))and succinonitrile(SN).The cosolvent fluoroethylene carbonate(FEC)optimizes the Li^(+)solvation structure in the SN-based electrolyte with its weakly solvating *** dynamics simulations investigate the regulating mechanism of ion-dipole and cation-anion *** unique Li^(+)solvation structure,enriched with FEC and TFSI^(-),facilitates the formation of an inorganic-organic composite solid electrolyte interphase on SiO ***-CT further detects the inhibiting effect on the SiO volume *** a result,the SiO|LiCoO_(2) full cells exhibit excellent electrochemical performance in deep eutectic-based *** work presents an effective strategy for extending the cycle life of SiO anodes by designing a new SN-based deep eutectic electrolyte.

关键词： Lithium-ion batteries Micrometer-sized silicon oxide Ion-dipole interaction Long-term cycling

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Graph Information Bottleneck for Multiview Molecular Embedding Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第4期5卷 1554-1562页

作者： Li, Changsheng Mao, Kaihang Wang, Shiye Yuan, Ye Wang, Guoren Beijing Institute of Technology School of Computer Science and Technology Beijing100081 China

In the field of computer-aided drug discovery, identifying promising drug candidates from small molecule libraries requires meaningful molecular embeddings for downstream tasks, such as property prediction. However, obtaining experimentally determined molecular property measurements is often expensive and time-consuming, making it challenging to train molecular encoders with limited supervision. In addition, molecules can be represented in two ways: as 2-D chemical-bond structures and 3-D geometry structures. Molecular embedding learning using only one of these representations can result in information loss, and effective fusion of the two views has not been fully explored. To address these challenges, we propose a new approach called the self-supervised multiview graph neural network (SMV-GNN) for molecular embedding learning. Our approach involves a self-supervised task that promotes the representation ability of the molecular encoder without requiring extra human-annotation data. Specifically, we use chemical-bond-based graph structures as inputs to predict interatom distances from the 2-D view and randomly shuffle a ratio of atoms in the 3-D coordinate-based graphs to predict atom rationality from the 3-D view. We further improve the representation ability of the molecular embedding by using information bottleneck to learn essential shared feature representations by discarding superfluous information from the 2-D/3-D views for downstream tasks. We evaluate our proposed SMV-GNN approach on seven benchmark datasets for molecule property-prediction tasks, and demonstrate that it outperforms the current state-of-the-art methods. © 2020 IEEE.

关键词： Atoms

来源：评论

学校读者我要写书评

暂无评论

SAT Problem Solving based on Hybrid Grey Wolf Genetic Algorithm 7

SAT Problem Solving based on Hybrid Grey Wolf Genetic Algori...

引用

7th International Conference on Intelligent Robotics and Control Engineering, IRCE 2024

作者： Li, Ya Sun, Yu Tong Lv, Hong Yang Chen, Lei Qu, Tian Wei Yun, Hai Hong Heilongjiang Institute of Technology College of Computer Science and Technology Harbin China Institute for Advanced Ceramics School of Materials Science and Engineering Harbin Institute of Technology Harbin China

ISBN: (纸本)9798350352399

A hybrid algorithm based on grey wolf optimization algorithm, genetic algorithm, and heuristic information is proposed for solving SAT problems. The algorithm is an incomplete algorithm. To solve the problem that the retention of dominant individuals in the standard genetic algorithm depends on selection probability, the grey wolf optimization algorithm is introduced into the crossover operator to increase the probability of inheriting dominant individuals to new generation. At the same time, there is also a significant randomness in mutation operation, which makes the entire algorithm prone to falling into local optima and the convergence speed is too slow. Therefore, in mutation operator, select those variables whose values can satisfy more clauses, to jump out of local optima while accelerating the convergence speed of the algorithm. Through comparative experiments, it was found that the algorithm proposed in this paper can quickly solve satisfying problems, and the algorithm is efficient and stable. © 2024 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Exoskeleton active assistance strategy for human muscle activation reduction during linear and circular walking

引用

Advances in Manufacturing 2024年第3期12卷 484-496页

作者： Wen-Tao Sheng Ke-Yao Liang Hai-Bin Tang School of Intelligent Manufacturing Nanjing University of Science and TechnologyNanjing210094People’s Republic of China School of Mechatronics Engineering Harbin Institute of TechnologyHarbin150001People’s Republic of China

The exoskeleton is employed to assist humans in various domains including military missions,rehabilitation,industrial operation,and activities of daily living(ADLs).Walking is a fundamental ADL,and exoskeletons are capable of reducing the activation and metabolism of lower extremity muscles through active assistance during *** improve the performance of active assistance strategy,this article proposes a framework using an active hip ***,it correlates to an already established Bayesian-based human gait recognition algorithm,with a particular focus on linear and circular walking within industrial and ADL *** theorizing this strategy for exoskeletons,this study further reveals,in part,the activation characteristics of human hip muscles for the instruction and regulation of active assistance duration and onset *** proposed active assistance strategy provides new insights for enhancing the performance of assistive robots and facilitating human robot interaction within the context of ADLs.

关键词： Human-robot interaction Hip exoskeleton Muscle activation Walking assistance

来源：评论

学校读者我要写书评

暂无评论

Efficient Top/Bottom-k Fraction Estimation in Spatial Databases Using Bounded Main Memory

引用

Tsinghua science and technology 2022年第2期27卷 223-234页

作者： Jinbao Wang Zhuojun Duan Xixian Han Donghua Yang School of Computer Science and Technology Harbin Institute of TechnologyHarbin 150001China Computer Science Department James Madison UniversityHarrisonburgVA 22807USA

Spatial databases store objects with their locations and certain types of attached items.A variety of modern applications have been developed by leveraging the utilization of locations and items in spatial objects,such as searching points of interest,hot topics,or users’attitude in specified spatial *** many scenarios,the high and low-frequency items in a spatial region are worth noticing,considering they represent the majority’s interest or eccentric users’***,existing works have yet to identify such items in an interactive manner,despite the significance of the endeavor in decision-making *** study recognizes a novel type of analytical query,called top/bottom-k fraction query,to discover such items in spatial *** achieve fast query response,we propose a multilayered data summary that is spread out across the main memory and external memory.A memory-based estimation method for top/bottom-k fraction queries is *** maximize the use of the main memory space,we design a data summary tuning method to dynamically allocate memory space among different spatial *** proposed approach is evaluated with real-life datasets and synthetic datasets in terms of estimation *** results demonstrate the effectiveness of the proposed data summary and corresponding estimation and tuning algorithms.

关键词： exploratory analytic top-k items bottom-k items spatial database

来源：评论

学校读者我要写书评

暂无评论

An integrated machine learning model for accurate and robust prediction of superconducting critical temperature

引用

Journal of Energy Chemistry 2023年第3期78卷 232-239,I0007页

作者： Jingzi Zhang Ke Zhang Shaomeng Xu Yi Li Chengquan Zhong Mengkun Zhao Hua-Jun Qiu Mingyang Qin X.-D.Xiang Kailong Hu Xi Lin School of Materials Science and Engineering Harbin Institute of TechnologyShenzhen 518055GuangdongChina Blockchain Development and Research Institute Harbin Institute of TechnologyShenzhen 518055GuangdongChina State Key Laboratory of Advanced Welding and Joining Harbin Institute of TechnologyHarbin 150001HeilongjiangChina School of Materials Science and Engineering Harbin Institute of TechnologyHarbin 150001HeilongjiangChina Department of Materials Science and Engineering&Department of Physics Southern University of Science and TechnologyShenzhen 518055GuangdongChina

Discovering new superconductors via traditional trial-and-error experimental approaches is apparently a time-consuming process,and the correlations between the critical temperature(Tc) and material features are still *** rise of machine learning(ML) technology provides new opportunities to speed up inefficient exploration processes,and could potentially uncover new hints on the unclear *** this work,we utilize open-source materials data,ML models,and data mining methods to explore the correlation between the chemical features and Tcvalues of superconducting *** further improve the prediction accuracy,a new model is created by integrating three basic algorithms,showing an enhanced accuracy with the coefficient of determination(R2) score of 95.9 % and root mean square error(RMSE) of 6.3 *** average marginal contributions of material features towards Tcvalues are estimated to determine the importance of various features during prediction *** results suggest that the range thermal conductivity plays a critical role in Tcprediction among all element ***,the integrated ML model is utilized to screen out potential twenty superconducting materials with Tcvalues beyond 50.0 *** study provides insights towards Tcprediction to accelerate the exploration of potential high-Tcsuperconductors.

关键词： Superconductors Integrated machine learning Superconducting critical temperature

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：