检索结果-内蒙古大学图书馆

SI of Interaction energy prediction of organic molecules using Deep Tensor Neural Network

Chinese Journal of chemical Physics 2021年第1期34卷 I0001-I0010页

作者： Yuan Qi Hong Ren Hong Li Dinglin Zhang Hongqiang Cui Junben Weng Guohui Li Guiyan Wang Yan Li Dalian Institute of Chemical Physics State Key Laboratory of Molecular Reaction DynamicsDalian116023China Aerospace Center Hospital Department of OphthalmologyBeijing100049China Dalian Naval Academy Department of Basic SciencesDalian116018China Harbin Engineering University College of Intelligent Systems Science and EngineeringHarbin150001China

The support informations of DTNN architecture and prediction results of six testing cases in K-fold are listed here.

关键词： Deep prediction listed

来源：评论

学校读者我要写书评

暂无评论

A Novel DWT-based Encoder for Human Pose Estimation

A Novel DWT-based Encoder for Human Pose Estimation

引用

2022 Scholar's Yearly Symposium of Technology, engineering and Mathematics, SYSTEM 2022

作者： De Magistris, Giorgio Romano, Matteo Starczewski, Janusz Napoli, Christian Department of Computer Control and Management Engineering Sapienza University of Rome Via Ariosto 25 Roma00185 Italy Department of Computational Intelligence Czstochowa University of Technology al. Armii Krajowej 36 Częstochowa42-200 Poland Institute for Systems Analysis and Computer Science Italian National Research Council Via dei Taurini 19 Roma00185 Italy

The proposed approach for pose estimation is based on the construction of a Convolutional Neural Network with an encoding-decoding structure and a spatial pyramid based on WASP structure in its bottleneck and a Discrete wavelet transform encoder. These techniques already shown their capabilities to solve the main problems in state of the art related to: different Field of view (FoV) required to analyze the different possible sizes of a specific subject. we want to solve the faulty structure of the modern CNN based Neural Networks in the encoding part using DWT encoder and WASP. This Work also have the objective of demonstrating from a more general point of view which could be the advantages of a Discrete Wavelet Transform (DWT) encoder in any CNN-based approach for Pose Estimation and Object detection in any form, such as for several subjects in the same image or in the internal video due to the almost redundant use of the usual most famous encoding structures for CNN such as ResNet-101, U-Net or VGG16-19. we will do our tests using a U-net Based CNN in order to evaluate the importance of the results of the Discrete Wavelet Transform encoder also in the decoding part through the cropping of theme at the last layers of the network. This is necessary due to the loss of border's pixels during encoding that could be useful for the result's evaluation. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0)

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Removal of petroleum asphaltenes by improved activity of NiO nanoparticles supported on green AlPO-5 zeolite: Process optimization and adsorption isotherm

引用

Petroleum 2020年第2期6卷 182-188页

作者： Majid Mohammadi Mehdi Sedighi Meysam Hemati Department of Energy Engineering Faculty of ScienceQom University of TechnologyQomIran Division of Energy Systems Department of Chemical EngineeringUniversity of QomQomIran Center of Environmental Research University of QomQomIran Department of Management Zanjan BranchIslamic Azad UniversityZanjanIran

Asphaltenes removal enhances the quality of the oil and facilitates the *** the present work,a NiO/AlPO-5 nanocomposite using green TMG was synthesized as a particular adsorbent for asphaltenes ***/AlPO-5 was characterized using FTIR,BET,TEM,and XRD *** Response Surface Method was used to optimize three important independent operating parameters,including D/C0[(g)adsorbent/(mg/L)initial](X1),initial pH(X2)and temperature(X3),to remove asphaltenes by the NiO/AlPO-5 nanocomposites in a model oil *** a CCD,a quadratic mathematical model formula was obtained to calculate asphaltene *** results revealed that the model showed valid agreement with the experimental results,with R2=*** optimum values for D/C0,pH as well as temperature would be 0.08[g/(mg/L)],3.39 and 298 K,*** was revealed that the optimal asphaltenes removal was 83.73%at the optimum *** isothermal models of Langmuir and Freundlich represented the asphaltenes adsorption on the new adsorbent with acceptable accuracy.

关键词： Asphaltene Removal Nanocomposite Optimization Adsorption

来源：评论

学校读者我要写书评

暂无评论

Meta-Reinforcement Learning for the Tuning of PI controllers: An Offline Approach

arXiv

引用

arXiv 2022年

作者： McClement, Daniel G. Lawrence, Nathan P. Backström, Johan U. Loewen, Philip D. Forbes, Michael G. Gopaluni, R. Bhushan Department of Chemical and Biological Engineering University of British Columbia VancouverBC Canada Department of Mathematics University of British Columbia VancouverBC Canada Backstrom Systems Engineering Ltd. Honeywell Process Solutions North Vancouver BC Canada Canada

Meta-learning is a branch of machine learning which trains neural network models to synthesize a wide variety of data in order to rapidly solve new problems. In process control, many systems have similar and well-understood dynamics, which suggests it is feasible to create a generalizable controller through meta-learning. In this work, we formulate a meta reinforcement learning (meta-RL) control strategy that can be used to tune proportional-integral controllers. Our meta-RL agent has a recurrent structure that accumulates "context" to learn a system's dynamics through a hidden state variable in closed-loop. This architecture enables the agent to automatically adapt to changes in the process dynamics. In tests reported here, the meta-RL agent was trained entirely offline on first order plus time delay systems, and produced excellent results on novel systems drawn from the same distribution of process dynamics used for training. A key design element is the ability to leverage model-based information offline during training in simulated environments while maintaining a model-free policy structure for interacting with novel processes where there is uncertainty regarding the true process dynamics. Meta-learning is a promising approach for constructing sample-efficient intelligent controllers. © 2022, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Atomistic Analysis on Implantation Effects of Hydrogen Ions and Copper Ions into 4h-Sic

SSRN

引用

SSRN 2024年

作者： Fang, Xudong Kang, Qiang Wu, Xiaoyu Fang, Ziyan Sun, Hao Wu, Chen Zhang, Zhongkai Verma, Prateek Maeda, Ryutaro Tian, Bian Kang, Chengwei State Key Laboratory for Manufacturing Systems Engineering International Joint Laboratory for Micro/Nano Manufacturing and Measurement Technologies Xi’an Jiaotong University Xi’an710049 China School of Mechanical Engineering Xi'an Jiaotong University Xi’an710049 China Shandong Laboratory of Advanced Materials and Green Manufacturing Yantai Yantai264000 China Department of Chemical Engineering University of Arkansas FayettevilleAR72701 United States School of Instrument Science and Technology Xi’an Jiaotong University Xi’an710049 China

Microstructure evolution of 4H-SiC by implantation of hydron ions and copper ions is investigated by molecular dynamics (MD) simulation and experiments. MD models of single Cu2+ and H+ implanting into SiC were established, respectively. During ion implantation, lattice damage, amorphous defects, and temperature distribution etc. were analyzed. Implantation of H+ induced more amorphous atoms than Cu2+. Maximum atomic temperature (1635K) of the model with Cu2+ was significantly higher than that of the model with H+ (950K), while the volume of temperature rising region in the model with H+ was much larger. Lattice vibration caused by Cu2+ was severer than that of H+ ions. Atoms on the crystal structure were prone to move along the region where the lattice binding energy was weak. The mechanism of overlapping multiple ions implanting was studied. Ion type, initial energy, and incident angle were varied. Sputtering yield, projection range, number of amorphous atoms, and energy increment of the model with Cu2+ were each smaller than those of H+. An incident angle of 0° induced higher sputtering yield and more amorphous structure due to the channeling effect. Channeling effect of H+ model was severer than that of Cu2+ model. Experimental results supported the MD simulation analysis. © 2024, The Authors. All rights reserved.

关键词： Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

Enhanced Mild Hydroisomerization of N-Heptane Over Bifunctional Pd@H-Yβ Zeolite Catalysts with Synergistic Acid and Pd Nanoparticles

SSRN

引用

SSRN 2023年

作者： Kang, Yu-Hong Zhang, Xiao-Qi Gao, Juan Wang, Yun-Fei Liu, Guang-Hui Li, Yan-Jun Gao, Yong Bai, Jin-Jun Wang, Ai-Min Wei, Xian-Yong Lu, Cui-Ying Shaanxi Key Laboratory of Low Metamorphic Coal Clean Utilization School of Chemistry and Chemical Engineering Yulin University Yulin719000 China Key Laboratory of Coal Processing and Efficient Utilization Ministry of Education China University of Mining & Technology Xuzhou221116 China Department of Chemical Engineering Ordos Institute of Technology Ordos017000 China Yulin Institute for Drug Control Yulin719000 China

Enhancing hydroisomerization efficiency and product selectivity by exploring the bifunctional zeolite-supported metal catalysts at the nanoscale are of great important in petrochemical and coal chemical industries. Herein, we explore a simple two-step strategy for introducing intracrystalline and intercrystalline mesopores in H-Yβ by in situ compositing and loading Pd nanoparticles (NPs, ~ 2.2 nm) through an incipient wetness impregnation process followed by mild oxidation-reduction treatment. Importantly, the Pd@H-Yβ catalyst with synergistic acid sites and minimizing Pd NPs inherits the large surface area, high crystallinity and mesopore porosity, and strong thermal and hydrothermal stability. As a demonstration, Pd@H-Yβ with extremely low Pd NPs loading amount of 0.2 wt% used for hydroisomerization of n-heptane by cascade dehydrogenation and hydrogenation on Pd NPs and isomerization on accessible acid sites, and exhibits an extraordinarily selectivity of i-heptane (74.7%) compared to the conventional Pd@H-Y (48.1%), Pd@H-β (33.4%), and Pd@HZSM-5 (0.1%) at 300 oC for 3 h under 1 MPa initial hydrogen pressure. Furthermore, first-principle calculations reveal that the excellent catalytic activity of Pd@H-Yβ originates from the active hydrogen (H…H and/or H+) transfer from the facile H2 dissociation. The diffusion limitations of intermediates and secondary cracking reactions are effectively weakened due to intrinsic mesopores in Pd@H-Yβ, which still maintains high catalytic activity after 5 times recycles. These findings provide a rational design strategy of bifunctional catalysts with metal-acid sites for low-molecular reactants conversion in industrial application. © 2023, The Authors. All rights reserved.

关键词： chemical industry

来源：评论

学校读者我要写书评

暂无评论

Data-driven Self-triggered control via Trajectory Prediction

arXiv

引用

arXiv 2022年

作者： Liu, Wenjie Sun, Jian Wang, Gang Bullo, Francesco Chen, Jie The State Key Lab of Intelligent Control and Decision of Complex Systems The School of Automation Beijing Institute of Technology Beijing100081 China The Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China The Mechanical Engineering Department The Center of Control Dynamical Systems and Computation UC Santa BarbaraCA93106-5070 United States The Department of Control Science and Engineering Tongji University Shanghai201804 China The State Key Lab of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing100081 China

Self-triggered control, a well-documented technique for reducing the communication overhead while ensuring desired system performance, is gaining increasing popularity. However, existing methods for self-triggered control require explicit system models that are assumed perfectly known a priori. An end-to-end control paradigm known as data-driven control learns control laws directly from data, and offers a competing alternative to the routine system identification-then-control method. In this context, the present paper puts forth data-driven self-triggered control schemes for unknown linear systems using data collected offline. Specifically, for output feedback control systems, a data-driven model predictive control (MPC) scheme is proposed, which computes a sequence of control inputs while generating a predicted system trajectory. A data-driven self-triggering law is designed using the predicted trajectory, to determine the next triggering time once a new measurement becomes available. For state feedback control systems, instead of capitalizing on MPC to predict the trajectory, a data-fitting problem using the pre-collected input-state data is solved, whose solution is employed to construct the self-triggering mechanism. Both feasibility and stability are established for the proposed self-triggered controllers, which are validated using numerical examples. © 2022, CC BY.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Coincidence analysis of Stackelberg and Nash equilibria in three-player leader-follower security games

arXiv

引用

arXiv 2022年

作者： Xu, Gehui Chen, Guanpu Cheng, Zhaoyang Hong, Yiguang Qi, Hongsheng Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Beijing China School of Mathematical Sciences University of Chinese Academy of Sciences Beijing China JD Explore Academy Beijing China Department of Control Science and Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China The Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China

There has been significant recent interest in leader-follower security games, where the leader dominates the decision process with the Stackelberg equilibrium (SE) strategy. However, such a leader-follower scheme may become invalid in practice due to subjective or objective factors, and then the Nash equilibrium (NE) strategy may be an alternative option. In this case, the leader may face a dilemma of choosing an SE strategy or an NE strategy. In this paper, we focus on a unified three-player leader-follower security game and study the coincidence between SE and NE. We first explore a necessary and sufficient condition for the case that each SE is an NE, which can be further presented concisely when the SE is unique. This condition not only provides access to seek a satisfactory SE strategy but also makes a criterion to verify an obtained SE strategy. Then we provide another appropriate condition for the case that at least one SE is an NE. Moreover, since the coincidence condition may not always be satisfied, we describe the closeness between SE and NE, and give an upper bound of their deviation. Finally, we show the applicability of the obtained theoretical results in several practical security cases, including the secure transmission problem and the cybersecurity defense. Copyright © 2022, The Authors. All rights reserved.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

The effect of cylinder wall cooling and vortex finder (tapered in-out) geometry on temperature, heat rate, and flow field to increase cyclone performance using CFD

引用

Case Studies in chemical and Environmental engineering 2023年 7卷

作者： Yohana, Eflita Tauviqirrahman, Mohammad Ismail, Rifky Muliyawan, Anggi Carles, Henry Dwinanda, M. Farkhan H. Ariyanto, H.D. Yulianto, M.E. Choi, Kwang-Hwan Department of Mechanical Engineering Diponegoro University Semarang 50275 Indonesia Departemen of Energy Conservation & Loss Control Engineering Development RU V Balikpapan PT Kilang Pertamina International Indonesia Diploma III Programme of Chemical Engineering Diponegoro University Indonesia College of Engineering Pukyong National University 365 Sinseon-ro Nam-gu Busan 608-739 South Korea

The results of testing the effect of temperature, flow field, heat transfer, and performance by simulating the tapered in-out shape with and without cylinder wall cooling (17 °C). The tapered in-out height variations used in this study are 0.5, 0.75, 1, and 1.25D with diameters De 74 and Dc 148. The fluid flow simulation used the RSM turbulence model. The particle movement approach is predicted using Eulerian-Lagrangian. The DPM method was applied to track the flow trajectories of individual particles. A model with cooling is applied to the cyclone body assuming constant temperature. The validation results of experimental and CFD simulation show the same trend with an error of 5.5%. Simulation results show that changing the shape of the vortex finder from the conventional cyclone (V0) to tapered in-out (V1) results in a significant improvement in performance: particle efficiency of 18.11% and pressure drop of 59.46%. The tapered in-out with cylinder wall cooling (V1C) slightly affects the performance: 1.9% increase in particle efficiency and 8.23% increase in pressure drop compared to the tapered in-out (V1). The change in height of V1 to V4 and V1C to V4C causes the performance on particle efficiency to decrease by 31.41% and 30.67% pressure drop decreases with increasing height of tapered in-out. © 2023

关键词： Cooling Heat transfer Particle efficiency Pressure drop Temperature Vortex finder

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "Release behaviors and catalytic effects of alkali and alkaline earth metals in coke from rapid pyrolysis of wheat straw" [J. Anal. Appl. Pyrolysis 190 (2025) 107160] (Journal of Analytical and Applied Pyrolysis (2025) 190, (S016523702500213X), (10.1016/***.2025.107160))

引用

Journal of Analytical and Applied Pyrolysis 2025年 190卷

作者： Wang, Jiaxi Ding, Lu Sun, Zhuang Guo, Qinghua Gong, Yan Yu, Guangsuo Institute of Clean Coal Technology East China University of Science and Technology Shanghai200237 China Shanghai Institute of Pollution Control and Ecological Security Shanghai200092 China Department of Transdisciplinary Science and Engineering School of Environment and Society Institute of Science Tokyo Tokyo152-8550 Japan State Key Laboratory of High-Efficiency Utilization of Coal and Green Chemical Engineering Ningxia University Yinchuan Ningxia750021 China

The authors regret that Dr. Lu Ding was not indicated as a corresponding author in the original article. Dr. Lu Ding should have been listed as a corresponding author with the email address: luding@***. The authors wo...

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：