检索结果-内蒙古大学图书馆

A Novel data-Driven Approach to analysis and Optimal Design of Forced Periodic Operation of Chemical Reactions

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2023年第8期70卷 8365-8376页

作者： Dong, Yuhan Lang, Zi-Qiang Zhao, Jun Wang, Wei Lan, Zhong Dalian Univ Technol Sch Control Sci & Engn Dalian 116024 Peoples R China Univ Sheffield Dept Automat Control & Syst Engn Sheffield S1 3JD S Yorkshire England East China Univ Sci & Technol Shanghai 200231 Peoples R China Dalian Univ Technol Inst Chem Engn Dalian 116024 Peoples R China

Forced periodic operation is a technique that periodically changes the manipulating variable of a chemical reaction system in order to exploit nonlinear dynamics to improve reactant conversion rate. However, the analysis and design of a periodically operated chemical process is a significant challenge. To resolve this problem, recently, nonlinear frequency response (NFR) based methods have been proposed. However, because of the need to derive the NFR from a first principle model, existing NFR methods can only perform qualitative analysis to simple processes and are often difficult to be applied in engineering practice. This article proposes a novel data driven approach to the analysis and optimal design of forced periodic operation of chemical reactions. From the data generated numerically using the first principle model or experimentally from experimental tests, the approach produces a data-driven NFR model that can readily be used for both quantitative study and optimal design of forced periodic operation of any complexities. This can fundamentally address the challenges faced by the existing NFR methods, and provides an effective approach that can potentially be applied in engineering practice. Simulation studies and experimental works are carried out on the application of the new method to an isothermal continuous stirred tank reactor system and a laboratory-scale carbon dioxide absorption process, respectively. The results verify the effectiveness and advantage of the newly proposed data driven approach and demonstrate the potential of the new approach in engineering applications.

关键词： Chemicals Chemical reactions Steady-state Analytical models Chemical processes Production Mathematical models analysis and optimal design data-driven modeling forced periodic operation nonlinear chemical system

来源：评论

学校读者我要写书评

暂无评论

Support for Building Infographic Models on the Multiforms Platform

Support for Building Infographic Models on the Multiforms Pl...

引用

2024 IEEE International Multi-conference on Engineering, Computer and Information Sciences, SIBIRCON 2024

作者： Korobko, Anna Benko, Nadezhda Erina, Irina Aldoshkina, Anna M. Reshetnev University Information Control Systems Department Krasnoyarsk Russia Institute of Computational Modeling Sb Ras Department of Information Technologies Krasnoyarsk Russia

ISBN: (纸本)9798331532024

The paper is devoted to the process of constructing infographic models for visualizing the results of analysis in BI-systems. The subject of research is the regularities of the choice of data visualization tools for an analytical query depending on the structure and properties of the data set using the Multiforms platform as an example. A formal description of the dataset data and metadata obtained as a result of executing a user request to a global analytical model on the Multiforms platform allows us to set a task of developing a new approach to the visualization of datasets that provides an informed choice of chart type, automatic determination of axes and displayed values. Based on the study of the visual components of the DevExteme library, it was possible to develop a general algorithm for native user support when choosing a diagram that best reflects the contents of the data. The considered examples illustrate the operation of the algorithm and make sure that the recommended ways of presenting data correspond to the structure of the dataset and display the content in the appropriate way. © 2024 IEEE.

关键词： data analysis exploratory OLAP flood situation visualization

来源：评论

学校读者我要写书评

暂无评论

Rubber Calendering Width Prediction Based on data Denoising and CNN-BiLSTM 14

Rubber Calendering Width Prediction Based on Data Denoising ...

引用

14th Asian control conference (ASCC)

作者： Zheng, Peiyu Yin, Xiaohong Li, Shaoyuan Qingdao Univ Sci & Technol Coll Automat & Elect Engn Qingdao Peoples R China

ISBN: (纸本)9798331540845;9789887581598

The rubber calendering process is critical in tire production, with the width of the rubber strip during calendering significantly impacting the final tire quality. This process is characterized by high noise, nonlinearity, temporal dependency, and pronounced dynamic features, which complicate the development of accurate models using traditional mechanistic modeling methods. To address this issue, a predictive model based on data denoising and a CNN-BiLSTM framework is proposed. The method employs improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) to decompose rubber calendering width data into multiple intrinsic mode functions (IMFs). Wavelet threshold denoising is then applied to high-frequency noise-containing IMFs, and the denoised IMFs are reconstructed to form a clean data series. Subsequently, a deep learning model combining convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) networks is developed to forecast the denoised rubber calendering width sequence. Comparative experiments demonstrate that this method effectively handles complex time-series data, with the model showing favorable evaluation metrics, highlighting significant advantages in predicting rubber calendering width.

关键词： rubber calendering ICEEMDAN wavelet threshold denoising convolutional neural network bidirectional long short-term memory network

来源：评论

学校读者我要写书评

暂无评论

Enhancing Time Series Prediction in Industrial processes: A Self-Attention BiLSTM Approach 7

Enhancing Time Series Prediction in Industrial Processes: A ...

引用

7th International conference on Robotics, control and Automation Engineering, RCAE 2024

作者： Wen, Sicheng Xu, Jiajun University of Engineering Science Department of Electronic and Electrical Engineering Shanghai Shanghai China University of Shanghai for Science and Technology Department of Optical-Electrical and Computer Engineering Shanghai China

ISBN: (纸本)9798350355642

The development of data-driven soft sensors for modeling complex data, particularly in scenarios characterized by strong nonlinearity, high dimensionality, cross-correlation and autocorrelation, remains a significant challenge in process data analysis. Bidirectional Long Short-Term Memory (BiLSTM) networks are highly effective in capturing both forward and backward dependencies within sequences, thereby enhancing the extraction of temporal features from time series data. However, BiLSTM networks may struggle to capture global dependencies, especially in long sequences. To address this limitation, the self-attention mechanism, which excels in modeling global relationships across all positions in the input sequence, can be integrated with BiLSTM by applying weighted attention to the two different directions of BiLSTM, thereby enhancing its performance. This study proposes a novel method called SA-BiLSTM, which combines the strengths of the BiLSTM network and the self- attention mechanism. The self-attention layer captures global dependencies, while the BiLSTM layer extracts comprehensive temporal features in both directions, which are then passed to a fully connected layer for final prediction. Extensive comparisons with traditional methods such as BiLSTM, LSTM with added self-attention mechanism, LSTM, RNN, and SVM validate the superior performance of the proposed SA-BiLSTM method in handling complex time series data. © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Torsional Stiffness analysis of Harmonic Drives Using Flexible Multibody Dynamics Simulation

引用

IEEE-ASME TRANSACTIONS ON MECHATRONICS 2023年第1期28卷 60-70页

作者： Lee, Joonho Han, Seok Hee Sohn, Jonghyeon Han, Byung-Kil Lee, Joo-Hong Park, Dong Il Kim, Jin-Gyun Korea Inst Machinery & Mat Dept Robot & Mech Daejeon 34103 South Korea Kyung Hee Univ Dept Mech Engn Integrated Engn Gyeonggi 17104 South Korea Korea Inst Machinery & Mat Dept Smart Ind Machine Technol Daejeon 34103 South Korea Korea Inst Machinery & Mat Dept Reliabil Assessment Daejeon 34103 South Korea

Predicting the nonlinear torsional stiffness of harmonic drives is important not only for system control but also for the further development of the drive. However, it is difficult to predict the torsional stiffness because of the elastic deformation of the flexspline and the many contacts involved. Furthermore, nonlinear dynamic contact simulations between the elastic components of the harmonic drive are disadvantaged by high computational burden and convergence problems. To address these challenges, we establish a flexible multibody modeling process using augmented formulations of a floating reference frame to simulate the operation of the harmonic drive. The elastic deformation of the flexspline and the dynamic contacts between the main components are considered in the reproduction of the contact mechanism of the drive. Coordinate reduction techniques are used to properly replicate an elastic shaft, enabling the effective simulation of flexible multibody dynamics, including nonlinear elastic tooth contact analysis. The performance of the proposed modeling process is evaluated using catalog and experimental data on two types of standard harmonic drives (SHG-25-100-UH and SHG-40-100-UH). The hysteresis curve is predicted through flexible multibody dynamics simulation and the accuracy of parameters of torsional stiffness is approximately 91.7% on average. The proposed modeling method can be improved to predict other measures of performance and it remains a potential research topic.

关键词： Harmonic analysis Mathematical models Strain Gears Analytical models Drives Computational modeling Dynamic contact analysis flexible multibody dynamics (FMBD) harmonic drive nonlinear torsional stiffness reduced-order modeling (ROM)

来源：评论

学校读者我要写书评

暂无评论

High-level optimization of industrial big data of DCC device based on neural network 3

High-level optimization of industrial big data of DCC device...

引用

3rd Asia-Pacific conference on Communications Technology and Computer Science (ACCTCS)

作者： Lu, Qi Tianjin Univ Technol Tianjin Peoples R China

ISBN: (纸本)9798350310801

The use of industrial big data high-level optimization to diagnose and analyze DCC devices has been applied in the petrochemical production process, promoting the revolutionary breakthrough of production process control. Combined with the company's idea of enhancing its core competitiveness through information technology, it then elaborates the existing data modeling methods, builds a software model, and tries to optimize its process big data and models through neural network algorithms to improve the potential of process control, so as to achieve the purpose of reducing costs and increasing efficiency. Finally, the characteristics of highlevel optimization of industrial big data and the problems and challenges that may be faced in the process of realizing this are discussed, in order to achieve a breakthrough in the company's overall business value.

关键词： big data neural networks process industries High-order optimization

来源：评论

学校读者我要写书评

暂无评论

Rumor Suppression in a Three-Layer Network: A Reinforcement Learning Algorithm

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2025年第3期12卷 2292-2307页

作者： Zhong, Xiaojing Zhang, Jing Wang, Aojing Liu, Guiyun Deng, Feiqi Wang, Jianhui Guangzhou Univ Sch Mech & Elect Engn Guangzhou 510006 Peoples R China South China Univ Technol Sch Automat Sci & Engn Guangzhou 510640 Peoples R China

Rumor propagation poses a significant threat to social stability and public order, and controlling its spread can effectively reduce unnecessary panic and misunderstanding. Rumor control is primarily achieved by simulating rumors spread on social networks and disseminating the truth or restricting propagation pathways. However, current studies usually only apply the optimal control theory, which leads to difficulties in coping with complex and stochastic network propagation environments. To address these issues, this paper constructs a three-layer network rumor control model (SICR-3M3W) that considers the dual refutation mechanism and formulates an optimal control problem for this model. Based on the reinforcement learning framework, we design a Proximal Policy Optimization (PPO) algorithm to solve this problem intelligently. Finally, experiments based on a real-world data case are conducted, and the results demonstrate that our three-layer model can effectively simulate the rumor propagation process. Moreover, the designed PPO controller can achieve optimal control outcomes.

关键词： Optimal control Media Reinforcement learning Social networking (online) Costs Biological system modeling Optimization Mathematical models Stochastic processes Heuristic algorithms Multi-layer network model stochastic dynamic analysis stochastic hybrid control reinforcement learning control algorithm real rumor datasets

来源：评论

学校读者我要写书评

暂无评论

An Efficient Method for Generating a Super-Sized and Heterogeneous Pore-Throat Network Model of Rock

引用

APPLIED SCIENCES-BASEL 2025年第3期15卷 1047-1047页

作者： Yu, Chunlei Chen, Wenbin Li, Junjian Wang, Shuoliang Sinopec Shengli Oilfield Branch Explorat & Dev Res Inst Dongying 257000 Peoples R China China Univ Geosci Beijing Sch Energy Resources Beijing 100083 Peoples R China China Univ Petr Sch Petr Engn Beijing 100100 Peoples R China

The super-sized pore-throat network model can reflect both microscopic pore characteristics and macroscopic heterogeneity and is excellent in describing cross-scale flow fields. At present, there is no algorithm that can generate a micro pore-throat network model at a macro reservoir scale. This study examines algorithms for super-sized pore-throat network reconstruction using actual core sample data. It conducts a random simulation of mineral growth and dissolution under the constraints of four microscopic pore structure parameters: porosity, coordination number, pore radius, and throat radius. This approach achieves high-precision, super-sized, and regional pore-throat network modeling. Comparative analysis shows that these four parameters effectively guide the random growth process of super-sized pore-throat networks. The overall similarity between the generated pore-throat network model and real core samples is 88.7% on average. In addition, the algorithm can partition and control the generation of pore-throat networks according to sedimentary facies. The 100-megapixel model with 85,000 pores was generated in 455.9 s. This method can generate cross-scale models and provides a basis for cross-scale modeling in physical simulation experiments and numerical simulations.

关键词： pore-throat network quartet structure generation set random growth partition control

来源：评论

学校读者我要写书评

暂无评论

modeling and analysis of external emergency response to ship fire using HTCPN and Markov chain

引用

OCEAN ENGINEERING 2024年 297卷

作者： Zhou, Chunhui Qin, Shixin Zhong, Jiahao Du, Lei Zhang, Fan Wuhan Univ Technol Sch Nav Wuhan Peoples R China Hubei Key Lab Inland Shipping Technol Wuhan Peoples R China CSSC Jiujiang Marine Equipment Grp Co Ltd Jiujiang Peoples R China China Lab Transport Pollut Control & Monitoring Te Beijing Peoples R China State Key Lab Maritime Technol & Safety Wuhan Peoples R China

The effectiveness of external emergency response to ship fires is critical in minimizing the serious consequences of ship fires. However, the insufficient consideration of the dynamic evolution of the emergency response may result in an inaccurate assessment of the effectiveness of ship fire emergency response. Therefore, we employ the theories of hierarchical timed colored Petri net (HTCPN) and Markov chains to evaluate the emergency response process to ship fire, and guide how to further improve emergency response capabilities. Firstly, the ship fire emergency response process is analyzed with ship fire emergency plans and accident cases. Next, the theory of Hierarchical Timed Colored Petri Net is adopted to model the ship fire emergency response process. Then, we calculated the performance metrics of the HTCPN model for ship fires using Markov chains, to identify the key nodes of this emergency response process. Several simulation experiments based on a fire accident data of "LONG QING 1 '' are conducted to demonstrate the feasibility of this proposed method. The key nodes of this emergency response process are identified as "emergency resource transportation", "firefighting operations", "surface search and rescue", and "developing emergency disposal plans". Some targeted suggestions for optimizing the emergency response process were put forward.

关键词： Ship fire Emergency response Petri net Markov chain

来源：评论

学校读者我要写书评

暂无评论

modeling and estimation of dynamics of time-delayed plants/processes

引用

INTERNATIONAL JOURNAL OF DYNAMICS AND control 2023年第1期11卷 183-193页

作者： Ghorai, Prasenjit Majhi, Somanath Eskandarian, Azim Pandey, Saurabh Kasi, Venkata Ramana Virginia Tech Dept Mech Engn Blacksburg VA 24060 USA Indian Inst Technol Guwahati Dept Elect & Elect Engn Gauhati 781039 Assam India Vellore Inst Technol Sch Elect Engn Vellore 632014 Tamil Nadu India

A real-time identification scheme based on relay autotuning and state-space analysis for the estimation of dynamics of time-delayed plants is proposed in this article. A set of mathematical expressions for parameter estimation of the process dynamics in the form of first- and second-order plus time delay transfer functions is derived. A relay with a hysteresis band is utilized for the mitigation of undesired noise content present at the process output in the noisy environment. The proposed method is studied on well-known process dynamics in comparison with the models available in the literature. After that, the relay autotuning tests (with and without hysteresis band) are conducted for the identification of dynamics of a real-time level control unit on a distributed control system platform with industry-standard field instruments. Finally, the experimental results from the relay tests are appended to show the practical applicability of the proposed modeling scheme and verify the dynamics in comparison with the actual data.

关键词： process dynamics Estimation and modeling State-space method Relay autotuning

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：