检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2023年第4期4卷 722-733页

作者： Li, Dong Liu, Yiqi Huang, Daoping Xu, Chong South China University of Technology Key Laboratory of Autonomous Systems and Networked Control Ministry of Education School of Automation Science and Engineering Guangzhou510640 China Technical University of Denmark Process and Systems Engineering Center Department of Chemical and Biochemical Engineering Lyngby2800 Denmark South China University of Technology School of Automation Science and Engineering Guangzhou510640 China Gannan Normal University School of Physics and Electronic Information Ganzhou341000 China

To monitor industrial processes properly, soft-sensors are widely used to predict significant but difficult-to-measure quality variables. However, the prediction performances of traditional data-driven soft-sensors are usually unacceptable once suffering from high-nonlinear, high-dimension, and imblance data issues. Therefore, a semisupervised soft-sensor, which is learned by a just-in-time method with structure entropy clustering (SS-JITL-SEC), is proposed aiming to improve prediction performance with a simpler way. Inspired by a divide and conquer strategy, a novel SEC method is proposed to achieve several clusters and then to translate the highly complex and nonlinear modeling problems into simple and linear ones. Moreover, the training dataset is extended through a mixed SS labeling approach. Finally, dissimilarity-based JITL works together with the resulting clustering subdatasets to formulate a local adaptive prediction model. Two datasets from different types of wastewater treatment plants are used to verify the effectiveness of the proposed soft-sensor. The results show that the SS-JITL-SEC soft-sensor can achieve better prediction performance than other standard counterparts, and even for effective process monitoring with the resulted residuals. © 2020 IEEE.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Higher N_(2)O production in sequencing batch reactors compared to continuous stirred tank reactors:effect of feast-famine cycles

引用

Frontiers of Environmental Science & engineering 2023年第4期17卷 143-154页

作者： Xinjie Yan Xunyu Shen Jipeng Wang Jinlong Zhuang Yu Wang Jinchi Yao Hong Liu Yongdi Liu James P.Shapleigh Wei Li National Engineering Research Center of Industrial Wastewater Detoxication and Resource Recovery East China University of Science and TechnologyShanghai 200237China 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 TechnologyShanghai 200237China School of Environmental and Safety Engineering Changzhou UniversityChangzhou 213164China Shanghai Huayi Group Co.Ltd. Shanghai 201108China Shanghai Institute of Pollution Control and Ecological Security Shanghai 200237China Department of Microbiology Cornell UniversityIthacaNY 14850USA

Nitrous oxide(N_(2)O)is a potent greenhouse gas that can be emitted during the biological treatment of *** this study,a comparison of the long-term performance characteristics and N_(2)O production of sequencing batch reactors(SBR)and continuous stirred tank reactors(CSTR)during nitrite-based denitrification was *** was found that both reactors had NO_(2)^(-)-N removal efficiencies over 99.9%,but the N_(2)O-N emissions from the SBR reached~2.3%of the removal nitrite-N load,while in the CSTR it never exceeded 0.1%.High frequency sampling during one operation cycle of the SBR demonstrated that the N_(2)O accumulation ratio was~0.1%during the feast period,increased to~1.9%in the first five hours of the famine period,and then gradually reached~2.3%at the end of *** experiments showed that limiting extracellular electron donor is required for N_(2)O accumulation in cells from the SBR-famine period and that cells from the CSTR do not accumulate N_(2)O when either nitrite or carbon is *** notable difference in the two reactor communities was the high level of accumulation of intracellular granules,most likely polyhydroxybutyrate(PHB),in cells during the feast period in the *** assembly and binning found that one genome(PRO1),which is a Thauera,accounted for over half the metagenomic reads in both *** shifts in gene regulation nor community composition explained the observed differences in reactor performance suggesting some post-transcriptional regulation obligatorily linked to antecedent conditions underly increased N_(2)O production in the SBR.

关键词： Denitrifying N_(2)O mitigation SBR CSTR Meta-omics PHB

来源：评论

学校读者我要写书评

暂无评论

On the use of Physics in Machine Learning for Manufacturing process Inspection 6

On the use of Physics in Machine Learning for Manufacturing ...

引用

Optical Methods for Inspection, Characterization, and Imaging of Biomaterials VI 2023

作者： Barbastathis, George Zhang, Qihang Pandit, Ajinkya Tang, Wenlong Papageorgiou, Charles Braatz, Richard D. Myerson, Allan S. Tan, Bingyao Schmetterer, Leopold Department of Mechanical Engineering Denmark Department of Chemical Engineering Massachusetts Institute of Technology United States Singapore-MIT Alliance for Research & Technology Centre Massachusetts Institute of Technology United States Data Sciences Institute United States Process Chemistry Development Takeda Pharmaceuticals International Company United States School of Chemistry Chemical Engineering and Biotechnology Nanyang Technological University Singapore

ISBN: (数字)9781510664548

ISBN: (纸本)9781510664531

We discuss the use of machine learning in computational imaging for manufacturing process inspection and control. In a recent article1 we described a physics-enhanced auto-correlation based estimator (Peace) for quantitative speckle. We derived an explicit forward relationship between the particle size distribution (PSD) and the speckle autocorrelation for particle sizes significantly larger than the wavelength (×100 „ ×1,000). We subsequently trained a machine learning kernel to invert the autocorrelation and obtain the PSD, using the explicit forward model to reduce the number of experimentally acquired examples. In this talk, we present an expanded discussion of Peace and its properties, including spatial and temporal sampling and accuracy, and more general applications. © 2023 SPIE. All rights reserved.

关键词： Autocorrelation

来源：评论

学校读者我要写书评

暂无评论

Physics-guided graph learning soft sensor for chemical processes

引用

Chemometrics and Intelligent Laboratory Systems 2024年 249卷

作者： Liu, Yi Jia, Mingwei Xu, Danya Yang, Tao Yao, Yuan Institute of Process Equipment and Control Engineering Zhejiang University of Technology Hangzhou310023 China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China Department of Chemical Engineering National Tsing Hua University Hsinchu300044 Taiwan

The surge in data-driven soft sensors for industrial processes is evident. However, most of them suffer from the limitation of being black-box models and this will hamper their widespread use. In response to this challenge, this study proposes a physics-guided graph-learning soft sensor that integrates a physical understanding of industrial processes by incorporating graph-based concepts with process physics. The soft sensor first constructs physical information based on causal relationships between variables using the conditional Granger causality test. Subsequently, it autonomously learns the unique sample information of each observation while employing a regularization loss to ensure the sparsity of the learned information. The model employs a two-stream structure for spatiotemporal encoding of both the physical and sample information. The modeling and prediction results on a penicillin fermentation process indicate that, using the proposed method, the knowledge gained from the data aligns with existing prior knowledge. This approach shows promise in filling the gap between data-driven and physics-based modeling in chemical processes. © 2024 Elsevier B.V.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Identification of Time-Delayed Second-Order Unstable Systems with Two Rhp Poles and No Zeros

SSRN

引用

SSRN 2023年

作者： Suhailam, P. Yerolla, Raju Besta, Chandra Shekar Process Control Group Chemical Engineering Department National Institute of Technology Calicut Kerala Kozhikode673601 India

New methods for identifying the model parameters of a pure unstable second-order system with time delay (two right-hand side poles without zero) using the closed-loop response are presented in this article. Identification of second-order systems with two unstable poles and no zeros is difficult due to the inherent instability, noise sensitivity, limited excitation possibilities, numerical challenges, and model validation issues associated with such systems. Expertise in system identification, control theory, and numerical methods is crucial when working with these complex dynamics. The process parameters of the transfer function are determined using the nonlinear least square optimization technique and particle swarm optimization technique. Analytical expressions are developed using the process responses to obtain the initial guess values for the model parameters. A mathematical procedure brings the initial guess values for parameters. The method is implemented on an unstable second-order with a time delay system, utilizing a feedback control method. The process response of the model identified by the proposed approaches to set point change compared with that of the actual process. Using both the Least Squares (LSQ) and Particle Swarm Optimization (PSO) methods is supported by evaluations against actual system performance criteria, revealing small but acceptable deviations like 0.88% in integral absolute error. The method is simple to implement and requires minimal processing time around 21 seconds. Developed methods for identifying the entire second-order unstable scalar system. © 2023, The Authors. All rights reserved.

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

GPP estimation of a grassland ecosystem based on photosynthesis-hydrology coordination optimization

GPP estimation of a grassland ecosystem based on photosynthe...

引用

2024 China Automation Congress, CAC 2024

作者： Fu, Lijiang Tan, Jinglu Jiang, Yongnian Allakhverdiev, Suleyman I. Xu, Zhenyu Guo, Ya Key Laboratory of Advanced Process Control for Light Industry Ministry of Education Jiangnan University Wuxi China Department of Chemical & Biomedical Engineering University of Missouri ColumbiaMO United States Jiangsu Zhongnong IoT Technology Co. LTD Yixing China Timiryazev Institute of Plant Physiology RAS Moscow Russia Longcom Internet of Things Co. Ltd Hefei China Key Laboratory of Advanced Process Control for Light Industry Ministry of Education Jiangnan University Wuxi China

ISBN: (纸本)9798350368604

Accurate estimation of gross primary production (GPP, ecosystem level photosynthesis) is critical for monitoring terrestrial ecosystems. However, most of the current models used for GPP estimation are with many unknown parameters and rarely include the effects of soil water stress due to the covariation of soil moisture and air humidity. In addition, grasslands, as the most widely distributed ecosystems in the world, have simple ecosystem structure and are easily affected by soil drought. Therefore, in this paper, we applied photosynthesis-hydrology coordination optimization theory and soil water potential based on soil moisture effect to develop a combined model (PH model) for GPP estimation of grassland ecosystems and used the US-Var grassland ecosystem, one of the FLUXNET sites from January to July 2004 (the driest period in recent years) as an example to validate the model. The results show that the model can effectively track the measured GPP during soil drought period and is better than the result from another commonly used photosynthesis coordination model (P-model) which does not consider the effect of soil drought. Further, we can infer the vegetation photosynthetic capacity parameters including the maximum carboxylation capacity (Vcmax) and the maximum electron-transport capacity (Jmax) under the effect of soil drought. The result also shows that if soil drought is not considered, the photosynthetic capacity parameters of vegetation will be overestimated. These results provide evidence for the application of photosynthesis-hydrology coordination theory in the assessment of ecosystem carbon cycle under the intensified climate changes. © 2024 IEEE.

关键词： coordination optimization theory GPP estimation soil drought

来源：评论

学校读者我要写书评

暂无评论

A classification AI model to predict choking of vibrating screen based on DEM and machine learning

引用

Powder technology 2025年 460卷

作者： Arifuzzaman, S.M. Dong, Kejun Zou, Ruiping Yu, Aibing Centre for Infrastructure Engineering School of Engineering Design and Built Environment Western Sydney University NSW2751 Australia ARC Research Hub for Smart Process Design and Control Department of Chemical Engineering Monash University ClaytonVIC3800 Australia

Screening is a complicated process for classifying granular materials according to size. Choking is a vital issue in screening. It may occur when the particle flow along a screen is too slow, but slow particle flow and long residence time are beneficial to sieving performance. Therefore, a model to judge whether choking happens is useful for finding optimal operating conditions. Here, a classification model to predict screen choking is proposed by combining DEM simulation and machine learning. The model can consider various key controlling variables for particle properties and operating conditions. Using the model, safe operation condition regions without choking can be identified. Then, combining the model with our previous machine learning based process model, we can design a screening process with the desired performance. The work also shows a way of using machine learning to predict critical phenomena in particle flow. © 2025 The Authors

关键词： Consolidation

来源：评论

学校读者我要写书评

暂无评论

Sustainable Water Use in Industry—Reasons, Challenges, Response of Kazakhstan

引用

Circular Economy and Sustainability 2023年第4期3卷 2267-2283页

作者： Radelyuk, Ivan Klemeš, Jiří Jaromír Tussupova, Kamshat Department of Chemistry and Chemical Technologies Toraighyrov University Pavlodar 140000 Kazakhstan Department of Water Resources Engineering Lund University Box 118 Lund 22100 Sweden Sustainable Process Integration Laboratory (SPIL) NETME CENTRE Faculty of Mechanical Engineering Brno University of Technology—VUT Brno Technická Brno 2896/2 616 69 Czech Republic

Industrial development poses significant challenges to water resource management, both in terms of quality and quantity. In response to these challenges, the concept of sustainable water use has been proposed as a means of addressing these issues. However, this concept is not yet widely adopted in developing countries, particularly in Kazakhstan. This paper examines the extent to which water use is sustainable on the example of the oil refinery sector in Kazakhstan. The investigation revealed a two-fold problem: the discharge of contaminated wastewater into the environment, which poses a risk of contamination transport, and the irrational use of water within the refinery. These issues are rooted in low water fees, low penalties for pollution and the gaps in legislation that allow for high maximum allowable concentrations of pollutants in discharges. As a result, toxic contaminants, such as petroleum hydrocarbons, are present in high concentrations exceeding permissible limits in groundwater up to 6 km away from the point of wastewater discharge. Based on the findings of the environmental impact assessments carried out in the sector, the authors propose a response that involves revising and implementing suitable legislative standards with requirements for transparent practices for environmental impact assessment and new efficient environmental monitoring programs to prevent water pollution. These measures have been adopted in the new Ecological Code and require proper control to ensure their effective implementation. However, the perspective of implementing efficient water-saving techniques and water integration is not yet widely visible and needs to be considered in order to achieve the sustainable water use in the industry. © 2023, The Author(s), under exclusive licence to Springer Nature Switzerland AG.

关键词： Best available techniques Circular economy Environmental impact assessment Industrial wastewater Sustainable water use Water integration

来源：评论

学校读者我要写书评

暂无评论

Critical Review of Hydrogen Safety Assessment Tools: Indian Perspective

引用

Transactions of the Indian National Academy of engineering 2024年第4期9卷 737-750页

作者： Rajagopal, Chitra Velpandian, Muthuraja Centre of Excellence in Process Safety & Risk management Indian Institute of Technology (IIT) Delhi New Delhi Delhi India Department of Chemical Engineering Indian Institute of Technology (IIT) Delhi New Delhi Delhi India

Hydrogen is widely regarded as a potentially viable solution for mitigating climate change and satisfying the growing need for sustainable energy sources. Its unique characteristics lead to both opportunities and challenges in its utilization. Significant safety concerns arise owing to its inherent properties and associated potential hazards. To ensure a smooth transition to a hydrogen economy, it is necessary to ensure its widespread acceptance among different stakeholders. This requires assurance of its safety and reliability throughout its value chain. A comprehensive systems safety analysis is strongly advocated for such a complex problem with uncertainties. It is crucial to create and share knowledge about its characteristics and behavior under the different scenarios likely to occur during its deployment in various sectors. A carefully tailored Quantitative Risk Assessment toolkit to facilitate the assessment of hazards and risks by stakeholders, evolution by consensus of a national risk acceptance criteria, maintaining an accessible database of failure rates, accidents/ incidents/ near misses, use of computational fluid dynamics, virtual reality, and augmented reality technologies for safety training and risk communication, as well as the use of big data, data analytics and digital technologies like virtual and e-labs to improve operational efficiency and safety, are the need of the hour. This paper reviews the work done in these areas globally and attempts to highlight existing gaps and a way forward for the country. The paper also reviews various evidence-based and risk-informed approaches adopted globally, in the development of regulations, codes and standards for hydrogen safety and the reforms needed in the regulatory framework to enable India to meet its goals of becoming a global hydrogen hub.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Numerical analysis of liquid flow in ironmaking blast furnace (BF) and its impact on BF performance

引用

Powder technology 2025年 462卷

作者： Liu, Yancong Jiao, Lulu Kuang, Shibo Yu, Aibing ARC Research Hub for Smart Process Design and Control Department of Chemical and Biological Engineering Monash University ClaytonVIC3800 Australia School of Metallurgical and Ecological Engineering University of Science and Technology Beijing Beijing100083 China

Various types of iron ores used in the blast furnace (BF) ironmaking process lead to different properties of the liquid flowing through the coke bed in the lower part, significantly influencing BF performance. This paper presents a numerical study of BF operations under different liquid conditions using a CFD process model. In this model, the force balance model that describes the liquid flow is modified to consider liquid viscosity and coke particle size explicitly. Using the model, the effects of different liquid viscosities corresponding to various iron ores are mainly studied based on a 5000-m3 industrial BF. These effects are also analyzed at various coke sizes. The numerical results show that as the liquid viscosity rises, the pressure drop first decreases and then increases, potentially leading to operation instability at high viscosities. These opposite trends of pressure drop result from the combined effects of increased liquid holdup and a thinned cohesive zone (CZ). Additionally, a higher liquid viscosity reduces the liquid temperature due to reduced solid-liquid heat transfer efficiency. The interaction between coke size and liquid viscosity complicates the above behavior, mainly through the influences on CZ thickness, liquid holdup, and solid-liquid heat transfer. This work provides insights to highlight the significance of liquid inside BF. © 2024

关键词： Iron analysis

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：