检索结果-内蒙古大学图书馆

Active training sample selection and updating strategy for near-infrared model with an industrial application

Chinese Journal of chemical Engineering 2019年第11期27卷 2749-2758页

作者： Kaixun He Kai Wang Yayun Yan College of Electrical Engineering and Automation Shandong University of Science and TechnologyQingdao 266590China Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of EducationEast China University of Science and TechnologyShanghai 200237China

Training sample selection is widely accepted as an important step in developing a near-infrared(NIR) spectroscopic model. For industrial applications, the initial training dataset is usually selected empirically. This process is time-consuming, and updating the structure of the modeling dataset online is difficult. Considering the static structure of the modeling dataset, the performance of the established NIR model could be degraded in the online process. To cope with this issue, an active training sample selection and updating strategy is proposed in this work. The advantage of the proposed approach is that it can select suitable modeling samples automatically according to the process information. Moreover, it can adjust model coefficients in a timely manner and avoid arbitrary updating effectively. The effectiveness of the proposed method is validated by applying the method to an industrial gasoline blending process.

关键词： Near-infrared spectroscopy chemical processes process systems Soft sensor Gasoline blending

来源：评论

学校读者我要写书评

暂无评论

Comparison of CNN-Uni-LSTM and CNN-Bi-LSTM based on single-channel EEG for sleep staging

Comparison of CNN-Uni-LSTM and CNN-Bi-LSTM based on single-c...

引用

International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)

作者： Qianyu Li Bei Wang Jing Jin Xingyu Wang Key Laboratory of Advanced Control and Optimization for Chemical Processes East China University of Science and Technology Shanghai China

ISBN: (数字)9781728180229

ISBN: (纸本)9781728180236

Sleep staging is an effective method for diagnosing sleep disorder and monitoring sleep quality. With the rapid development of machine learning technology, the automatic staging methods of sleep gradually replace the traditional manual interpretation which can improve the efficiency on sleep staging for medical research. LSTM networks can save the historical information as a reference for the current moment, which is undoubtedly a good way to improve sleep staging performance. In this paper, a convolutional neural network (CNN) is constructed to extract the features from a single-channel EEG. The Uni-directional Long Short-Term Memory (Uni-LSTM) network and Bi-directional Long Short-Term Memory (Bi-LSTM) network are combined with CNN to realize automatic sleep staging. The obtained results showed that the two presented network frameworks are effective and feasible on sleep staging. The Bi-LSTM which has more enriched sequence information got better classification performance than the Uni-LSTM.

关键词： Sleep Manuals Machine learning Feature extraction Electroencephalography Monitoring Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Submodularity-based sensor scheduling for state estimation among multiple linear dynamical systems

Submodularity-based sensor scheduling for state estimation a...

引用

Jiangsu Annual Conference on Automation (JACA 2022)

作者： Y. Ni C. Yang X. Liu X. Luan F. Liu The Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education) School of Internet of Things Engineering Jiangnan University Wuxi People's Republic of China The Key Laboratory of Smart Manufacturing in Energy Chemical Process (Ministry of Education) Department of Automation East China University of Science and Technology Shanghai People's Republic of China Department of Radiology Athinoula A. Martinos Center for Biomedical Imaging Massachusetts General Hospital/Harvard Medical School Boston USA

In this paper we focus on the sensor scheduling for dynamic state estimation among multiple processes. Multiple sensors transmit their measurements to the remote estimator via a shared wireless channel. Only a subset of sensors are allowed to transmit at each time. The objective of the scheduler is to maximize a linear combination of the terminal time estimation error covariances in a log-determinant sense. We develop conditions under which the objective is monotone and submodular. A submodularity-based greedy scheduling algorithm is proposed, and its performance bound is provided. Numerical examples are presented to illustrate the theoretical findings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Representation evaluation block-based teacher-student network for the industrial quality-relevant performance modeling and monitoring

arXiv

引用

arXiv 2021年

作者： Yang, Dan Peng, Xin Lu, Yusheng Huang, Haojie Zhong, Weimin Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education East China University of Science and Technology Shanghai200237 China Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai200092 China

Quality-relevant fault detection plays an important role in industrial processes, while the current quality-related fault detection methods based on neural networks main concentrate on process-relevant variables and ignore quality-relevant variables, which restrict the application of process monitoring. Therefore, in this paper, a fault detection scheme based on the improved teacher-student network is proposed for quality-relevant fault detection. In the traditional teacher-student network, as the features differences between the teacher network and the student network will cause performance degradation on the student network, representation evaluation block (REB) is proposed to quantify the features differences between the teacher and the student networks, and uncertainty modeling is used to add this difference in modeling process, which are beneficial to reduce the features differences and improve the performance of the student network. Accordingly, REB and uncertainty modeling is applied in the teacher-student network named as uncertainty modeling teacher-student uncertainty autoencoder (TSUAE). Then, the proposed TSUAE is applied to process monitoring, which can effectively detect faults in the process-relevant subspace and quality-relevant subspace simultaneously. The proposed TSUAE-based fault detection method is verified in two simulation experiments illustrating that it has satisfactory fault detection performance compared to other fault detection methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Wastewater treatment

来源：评论

学校读者我要写书评

暂无评论

Distribution Adaptation Local Outlier Factor for Multimode process monitoring

Distribution Adaptation Local Outlier Factor for Multimode P...

引用

第三十九届中国控制会议

作者： Yutang Xiao Yang Tao Hongbo Shi Key Laboratory of Advanced Control and Optimization for Chemical Processes of the Ministry of Education East China University of Science and Technology

In modern industrial processes, the production process includes multiple operating modes, due to changes in production goals and conditions. And the data generated in this process is a mixture of Gaussian and non-Gaussian distributions. Therefore, the data distribution of multimode processes is uncertain and complex. It is difficult to monitor multimode processes accurately by using traditional Multivariate Statistical process Monitoring（MSPM） methods. In this case, the absence of labeled data is considered more valuable. This paper proposes a new unsupervised domain adaptive method called the Distribution Adaptation Local Outlier Factor（DALOF）. This method can extract useful information from multimode data through domain adaptation, which can reduce the distribution difference of training data and improve the accuracy of modeling. In the DALOF model, data from different modes in the training set are defined as the source domain and the target domain. Weight the training data according to their correlation, and then project these data into a low-dimensional subspace. In this space, the distribution distance between the source and target domain is minimum. To solve the nonlinear characteristics of multimode data, this paper uses LOF to build a model and formed a density-based monitoring index. Numerical examples and Tennessee Eastman（TE） process simulation demonstrate the effectiveness of DALOF.

关键词： Distribution Adaptation Local Outlier Factor Multimode process process monitoring

来源：评论

学校读者我要写书评

暂无评论

Study on Flue Gas Desulfurization process with Selective SO2 Removal by N-formylmorpholine

引用

China Petroleum processing & Petrochemical Technology 2019年第2期21卷 85-94页

作者： Long Jian Wang Jin Fan Chen Yang Minglei Zhong Weimin Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education East China University of Science and Technology Shanghai 200237 SINOPEC Zhenhai Refining and Chemical Co. Ltd. Ningbo 315207

Absorptive separation for resource utilization by selective SO2 removal from flue gas is a potential method applicable in practice. A flue gas desulfurization process for SO2 utilization by selective absorption in a lab-scale absorption tower at atmospheric pressure using N-formylmorpholine (NFM) as the absorbent is developed to capture and concentrate the SO2 from flue gas, in which the CO2 content is several orders higher than that of SO2. The investigation of the effects of different operating conditions on the SO2 removal efficiency shows that the SO2 removal efficiency can be obviously enhanced by increasing NFM concentration, or decreasing the absorption temperature, the superficial gas velocity, the gas-liquid ratio, or the SO2 concentration in absorption solution. Under the optimum operating conditions (covering a temperature of 40 °C, a superficial gas velocity of <0.0165 m/s, a gas-liquid ratio of 200—250, a SO2 concentration in lean NFM solution of 0—10 mg/L, and a NFM concentration of 3 mol/L), the SO2 removal rate reaches over 99.5% while the absorption of CO2 is negligible. Similarly, the SO2 removal rate is as high as 99.5% obtained in consecutive absorption-desorption cycles. Desorption experiment results indicate that the absorption of sulfur dioxide is completely reversible and the release of SO2 from NFM is very easy and rapid at 104 °C. The absorption simulation result for desulfurization of flue gas vented from the industrial catalytic cracking regenerator shows that 98.0% of SO2 can be absorbed in the absorber and most of them are released in the desorber. The experimental and simulated results show that the desulfurization ability and regenerability of NFM solution is encouraging for the development of FGD process to capture the SO2 from flue gas.

关键词： flue gas desulfurization selective SO2 removal N-formylmorpholine absorption simulation

来源：评论

学校读者我要写书评

暂无评论

Modeling of oil near-infrared spectroscopy based on similarity and transfer learning algorithm

引用

Frontiers of chemical Science and Engineering 2019年第3期13卷 599-607页

作者： Yifei Wang Kai Wang Zhao Zhou Wenli Du Key Laboratory of Advanced Control and Optimization for Chemical Processes (Ministry of Education) East China University of Science and TechnologyShanghai 200237China School of information science and engineering East China University of Science and TechnologyShanghai 200237China

Near-infrared spectroscopy mainly reflects the frequency-doubled and total-frequency absorption information of hydrogen-containing groups (0 -H, C-H, N-H, S-H) in organic molecules for near-infrared lights with different wavelengths, so it is applicable to testing of most raw materials and products in the field of petrochemicals. However, the modeling process needs to collect a large number of laboratory analysis data. There are many oil sources in China, and oil properties change frequently. Modeling of each raw material is not only unfeasible but also will affect its engineering application efficiency. In order to achieve rapid modeling of near-infrared spectroscopy and based on historical data of different crude oils under different detection conditions, this paper discusses about the feasibility of the application of transfer learning algorithm and makes it possible that transfer learning can assist in rapid modeling using certain historical data under similar distributions under a small quantity of new data. In consideration of the requirement of transfer learning for certain similarity of different datasets, a transfer learning method based on local similarity feature selection is proposed. The simulation verification of spectral data of 13 crude oils measured by three different probe detection methods is performed. The effectiveness and application scope of the transfer modeling method under different similarity conditions are analyzed.

关键词： near-infrared spectroscopy transfer learning similarity modeling

来源：评论

学校读者我要写书评

暂无评论

Zoning search using a hyper-heuristic algorithm

引用

Science China(Information Sciences) 2019年第9期62卷 193-195页

作者： Qinqin FAN Ning LI Yilian ZHANG Xuefeng YAN Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai Jiao Tong University Logistics Research Center Shanghai Maritime University Key Laboratory of Marine Technology and Control Engineering Ministry of CommunicationsShanghai Maritime University Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education East China University of Science and Technology

Dear editor,With the development of high-performance computing techniques, run time of meta-heuristic algorithms can be reduced effectively. However, improved computation power has not been indirectly converted into search capability in most of previous studies [1]. Moreover, the solution precision of an optimization problem is directly determined

关键词： pro CEC Zoning search using a hyper-heuristic algorithm

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Anion Exchange and Reverse Electron Transfer in Ldh/Peroxymonosulfate System for Roxarsone Elimination

SSRN

引用

SSRN 2024年

作者： Pei, Wenkai Zheng, Yifan Gao, Jianyu Lei, Juying Liu, Yongdi Zhou, Liang Zhang, Jinlong Wang, Yu National Engineering Research Center of Industrial Wastewater Detoxication and Resource Recovery State Environmental Protection Key Laboratory of Environmental Risk Assessment and Control on Chemical Process East China University of Science and Technology Shanghai200237 China Shanghai Engineering Research Center for Multi-media Environmental Catalysis and Resource Utilization Key Laboratory for Advanced Materials Joint International Research Laboratory of Precision Chemistry and Molecular Engineering Feringa Nobel Prize Scientist Joint Research Center School of Chemistry and Molecular Engineering East China University of Science and Technology 130 Meilong Road Shanghai200237 China Department of Molecular Engineering Graduate School of Engineering Kyoto University Kyoto-Daigaku Katsura Nishikyo-ku Kyoto615-8510 Japan State Key Laboratory of Urban Water Resource and Environment Harbin Institute of Technology Harbin150090 China Shanghai Institute of Pollution Control and Ecological Security Shanghai200092 China

Roxarsone (ROX) is the main form of As pollution in the world, and developing effective methods for its elimination is beneficial to human health and ecological environment. Herein, we report glutaraldehyde-crosslinked chitosan encapsulated CoCe-LDH as an outstanding catalyst for the advanced oxidation of ROX and the efficient adsorption of inorganic arsenic. 100% of ROX and more than 98.5% of As(III)/As(V) were eliminated, and over 99.3% of remained inorganic arsenic was oxidized to low toxicity As(V) in the PMS-activation system, and some specific properties of LDH are considered the main reasons. The hierarchical anion exchange has been confirmed to be beneficial for constructing a high concentration PMS inter layer microenvironment. And the unique reverse electron transfer process induced the 100% selective production of singlet oxygen. This work not only develops an advanced ROX removal method, but also provides a new understanding of LDH-based advanced oxidation process. © 2024, The Authors. All rights reserved.

关键词： chemical activation

来源：评论

学校读者我要写书评

暂无评论

A Binary Dumbbell Visible Light Driven Photocatalyst for Simultaneous Hydrogen Production with the Selective Oxidation of Benzyl Alcohol to Benzaldehyde

SSRN

引用

SSRN 2024年

作者： Tayyab, Muhammad Mansoor, Seemal Akmal, Zeeshan Khan, Mazhar Zhou, Liang Lei, Juying Zhang, Jinlong Key Laboratory for Advanced Materials Shanghai Engineering Research Center for Multimedia Environmental Catalysis and Resource Utilization Joint International Research Laboratory of Precision Chemistry and Molecular Engineering Feringa Nobel Prize Scientist Joint Research Center School of Chemistry and Molecular Engineering East China University of Science and Technology Shanghai200237 China Institute of Materials Research Tsinghua Shenzhen International Graduate School Tsinghua University Guangdong Shenzhen518055 China National Engineering Research Center of Industrial Wastewater Detoxication and Resource Recovery State Environmental Protection Key Laboratory of Environmental Risk Assessment and Control on Chemical Process East China University of Science and Technology Shanghai200237 China Shanghai Institute of Pollution Control and Ecological Security Shanghai200092 China State Key Laboratory of Urban Water Resource and Environment Harbin Institute of Technology Harbin150090 China

Photocatalytic H2 production with selective oxidation of organic moieties in an aqueous medium is a fascinating research area. However, the rational design of photocatalysts and their photocatalytic performance are still inadequate. In this work, we efficiently synthesized the MoS2 tipped CdS nanowires (NWs) photocatalyst using soft templates via the two-step hydrothermal method for efficient H2 production with selective oxidation of benzyl alcohol (BO) under visible light illumination. The optimized MoS2 tipped CdS NWs (20% MoS2) photocatalyst exhibits the highest photocatalytic H2 production efficiency of 13.55 mmol g-1 h-1 with 99% selective oxidation of BO, which was 42.34 and 2.21 times greater photocatalytic performance than that of pristine CdS NWs and MoS2/CdS NWs, respectively. The directional loading of MoS2 at the tips of CdS NWs (as compared to nondirectional MoS2 at CdS NWs) is the key factor towards superior H2 production with 99% selective oxidation of BO and has an inhibitory effect on the photo corrosion of pristine CdS NWs. Therefore, the amazing enhancement in the photocatalytic performance and selectivity of optimized MoS2 tipped CdS NWs (20% MoS2) photocatalyst is due to the spatial separation of their photoexcited charge carriers through the Schottky junction. Moreover, the unique structure of MoS2 flower at the tip of 1D CdS NWs offers separate active sites for adsorption and surface reactions such as H2 production at the MoS2 flower (confirmed by Pt photo deposition) and subsequently the selective oxidation of BO at the stem of CdS NWs. This rational design of a photocatalyst could be an inspiring work for the further development of efficient photocatalytic system for H2 production with selective oxidation of BO (a strategy of mash two potatoes with one fork). © 2024, The Authors. All rights reserved.

关键词： Precious metals

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：