检索结果-内蒙古大学图书馆

Big Data Capabilities Applied to Semiconductor Manufacturing advanced process control

IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING 2016年第4期29卷 283-291页

作者： Moyne, James Samantaray, Jamini Armacost, Michael Appl Mat Inc Santa Clara CA 95054 USA

As requirements on data volumes, rates, quality, merging, and analytics increase exponentially in the digital universe, semiconductor manufacturers are faced with a need for new approaches to data management and use across the Fab. These are often termed "big data" challenges. In our industry big data solutions will be key to scaling advanced process control (APC) solutions to finer levels of control and diagnostics. However the main impact will be to better enable more effective predictive technologies such as predictive maintenance (PdM), virtual metrology and yield prediction, all of which utilize data from traditional APC capabilities that include fault detection and classification and run-to-run control. PdM represents one area where big data solutions are generating significant benefits across a variety of process types. Moving to big data solutions involves addressing the aforementioned requirements either with enhancements of existing systems or moving to more big data friendly platforms. Big data friendly platforms applied to APC systems provide quantifiable cost-of-ownership and speed improvements, thereby better enabling high quality prediction solutions. Initially, big data solutions will largely be delegated to off-line and on-time critical tasks;over the longer term these big data solutions will increasingly be leveraged for time critical and real-time capabilities.

关键词： advanced process control big data database management systems hadoop prediction methods predictive control predictive maintenance process control virtual metrology yield prediction

来源：评论

学校读者我要写书评

暂无评论

Next Generation advanced process control: Leveraging Big Data and Prediction 27

Next Generation Advanced Process Control: Leveraging Big Dat...

引用

27th Annual SEMI advanced Semiconductor Manufacturing Conference (ASMC)

作者： Moyne, James Schulze, Brad Iskandar, Jimmy Armacost, Michael Appl Mat Appl Global Serv Santa Clara CA 95054 USA

ISBN: (纸本)9781509002702

advanced process control (APC), which includes run-to-run (R2R) process control and fault detection and classification (FDC) is pervasive in fabs today. While APC provides many benefits, it also presents many implementation and operational challenges including significant up-front configuration cost, lack of solution accuracy resulting in false/missed alarms, and lack of a consistent capability for prognostics leading to scrap, lost productivity and reduced quality. Next Generation APC (NG-APC) is an evolutionary solution that addresses these challenges and provides new capabilities for APC solutions. It leverages recent advancements in the traditional APC capabilities as well as benefits provided by big data and prediction capabilities. Key enhancements include single-threaded R2R control for improved high-mix process control capability, semi-automation of FDC model development with model and limits optimization through a move to "supervised" FDC, improved data management and analysis capabilities through leveraging of big data architectures, and incorporation of prediction capabilities in solutions for improved process quality and uptime with reduced cost. Additionally, NGAPC is structured as an extensible solution, thus it can continue to evolve as new APC and related technologies emerge.

关键词： advanced process control APC Big Data Fault Detection and Classification FDC Run-to-Run control R2R control Prediction Predictive Maintenance Virtual Metrology

来源：评论

学校读者我要写书评

暂无评论

advanced process control APPLICATIONS FOR advanced CMP process

ADVANCED PROCESS CONTROL APPLICATIONS FOR ADVANCED CMP PROCE...

引用

China Semiconductor Technology International Conference

作者： Yang, Jun Lin, Yi Shih Yang, SiYuan Frank Huang, Yi Shao, Qun Liu, Hongtao Semicond Mfg Int Shanghai Corp Shanghai 201203 Peoples R China

ISBN: (纸本)9781479972425

There are increasing new needs for advanced process control (APC) from chemical mechanical polishing (CMP) process along with the technology nodes advancing to 28nm and below. Besides traditional applications for wafer to wafer and batch to batch thickness variation reduction, and feed-forward based on incoming thickness/depth, the other new needs include within wafer uniformity control based on consumable counts and incoming profile, preventing polishing rate from dropping due to disk and pad deteriorating etc. This paper discusses those APC applications for CMP processes and along with important features which advanced APC software should equip with.

关键词： advanced process control chemical mechanical polishing profile control run to run control partition safety guarding features

来源：评论

学校读者我要写书评

暂无评论

Application of advanced process control techniques for a Cement Rotary Kiln 19

Application of Advanced Process Control techniques for a Cem...

引用

19th International Conference on System Theory, control and Computing (ICSTCC)

作者： Zanoli, S. M. Pepe, C. Rocchi, M. Astolfi, G. Univ Politecn Marche UNIVPM DII Via Brecce Bianche I-60131 Ancona AN Italy I Proc Srl Via Consorzio 2 Falconara M Ma AN Italy

ISBN: (纸本)9781479984817

In this work, the control optimization of a rotary kiln located in a cement plant is described. The need to enhance the efficiency level, to increase the profitability as well as the commitment to meet precise production standards has motivated the adoption of Model Predictive control techniques. The adopted system architecture is composed of two different optimization layers. A suitable interaction policy has been developed so as to improve control performances and to meet possibly variable economic goals. The advantages of the proposed architecture are shown by significant simulations. The developed predictive control system has been implemented on real plant and its overall performances are compared to the performances of the previous standard PID control system. Very satisfactory system performances have been achieved been able to attain both economic benefits and minimization of environmental noxious emissions.

关键词： advanced process control Model Predictive control economic optimization enviromental emissions cement rotary kiln

来源：评论

学校读者我要写书评

暂无评论

advanced process control Application and Optimization in Industrial Facilities

引用

KEMIJA U INDUSTRIJI-JOURNAL OF CHEMISTS AND CHEMICAL ENGINEERS 2015年第1-2期64卷 39-48页

作者： Howes, S. Mohler, I. Bolf, N. PiControl Solut Houston TX USA Univ Zagreb Fac Chem Engn & Technol Savska C 16-5a Zagreb 10000 Croatia

This paper describes application of the new method and tool for system identification and PID tuning/advanced process control (APC) optimization using the new 3G (geometric, gradient, gravity) optimization method. It helps to design and implement control schemes directly inside the distributed control system (DCS) or programmable logic controller (PLC). Also, the algorithm helps to identify process dynamics in closed-loop mode, optimizes controller parameters, and helps to develop adaptive control and model-based control (MBC). Application of the new 3G algorithm for designing and implementing APC schemes is presented. Optimization of primary and advanced control schemes stabilizes the process and allows the plant to run closer to process, equipment and economic constraints. This increases production rates, minimizes operating costs and improves product quality.

关键词： System identification controller tuning and optimization advanced process control model based control

来源：评论

学校读者我要写书评

暂无评论

Open Cloud Solution for Integrating advanced process control in Plant Operation 23

Open Cloud Solution for Integrating Advanced Process Control...

引用

23rd Mediterranean Conference on control and Automation (MED)

作者： Chenaru, Oana Stanciu, Alexandru Popescu, Dan Sima, Vasile Florea, Gheorghe Dobrescu, Radu SIS Bucharest Romania Natl Inst Res & Dev Informat Bucharest Romania Politehn Univ Fac Automat Control & Comp Sci Bucharest Romania

ISBN: (纸本)9781479999361

This paper presents a model for integrating an advanced process control library in a cloud-based environment. The aim is to lower the development times, to reduce maintenance effort and decrease the complexity of process control applications by adopting a modular approach consisting of generic, reusable control strategies following an IEC 61499 representation. The solution uses open cloud technologies based on Heroku for the deployment in a public cloud structure and Docker for increased portability of the designed solution. The conceptual architecture of the system is presented, as well as the details of the execution module.

关键词： Cloud computing advanced process control Service-Oriented Architecture (SOA) IEC 61499 remon execution web services

来源：评论

学校读者我要写书评

暂无评论

Next Generation advanced process control: Leveraging Big Data and Prediction

Next Generation Advanced Process Control: Leveraging Big Dat...

引用

Annual SEMI advanced Semiconductor Manufacturing Conference

作者： James Moyne Brad Schulze Jimmy Iskandar Michael Armacost Applied Materials—Applied Global Services Santa Clara CA USA

advanced process control (APC), which includes run-to-run (R2R) process control and fault detection and classification (FDC) is pervasive in fabs today. While APC provides many benefits, it also presents many implementation and operational challenges including significant up-front configuration cost, lack of solution accuracy resulting in false/missed alarms, and lack of a consistent capability for prognostics leading to scrap, lost productivity and reduced quality. Next Generation APC (NG-APC) is an evolutionary solution that addresses these challenges and provides new capabilities for APC solutions. It leverages recent advancements in the traditional APC capabilities as well as benefits provided by big data and prediction capabilities. Key enhancements include single-threaded R2R control for improved high-mix process control capability, semi-automation of FDC model development with model and limits optimization through a move to "supervised" FDC, improved data management and analysis capabilities through leveraging of big data architectures, and incorporation of prediction capabilities in solutions for improved process quality and uptime with reduced cost. Additionally, NG-APC is structured as an extensible solution, thus it can continue to evolve as new APC and related technologies emerge.

关键词： advanced process control APC Big Data Fault Detection and Classification FDC Run-to-Run control R2R control Prediction Predictive Maintenance Virtual Metrology

来源：评论

学校读者我要写书评

暂无评论

A systematic modeling approach for continuous flow synthesis applicable to real-time process control

引用

CHEMICAL ENGINEERING RESEARCH & DESIGN 2025年 216卷 322-332页

作者： Rehrl, Jakob Celikovic, Selma Castillo, Ismael Kruisz, Julia Sagmeister, Peter Lebl, Rene Williams, Jason D. Sacher, Stephan Kappe, C. Oliver Khinast, Johannes Horn, Martin Res Ctr Pharmaceut Engn GmbH Inffeldgasse 13 A-8010 Graz Austria Graz Univ Technol Inst Automat & Control Inffeldgasse 21-B A-8010 Graz Austria Inst Proc & Particle Engn Inffeldgasse 13-3 A-8010 Graz Austria Karl Franzens Univ Graz NAWI Graz Inst Chem Heinrichstr 28 A-8010 Graz Austria

The application of process analytical technology to continuous flow processes offers several advantages, including real-time process monitoring and the implementation of process control strategies. Model-based control approaches, such as model predictive control, provide significant benefits in flow processes, enabling flexible formulation of control objectives (e.g., maximizing yield while minimizing by-products and considering equipment limitations). A key requirement for such control strategies is the availability of suitable process models. This paper outlines the systematic development of process models for a continuous mesalazine synthesis process, including nitration, hydrolysis, and hydrogenation. Classical process design methods, including Design of Experiments (DoE) and DoE-based static models, were employed to systematically determine optimal operating conditions (e.g., maximizing yield). To maintain the process at this optimum through model-based control, models that capture process dynamics are required. Therefore, mechanistic process models, based on reaction kinetics, were implemented and parametrized. While these models effectively represent the dynamic behavior, their high computational load limits their applicability for real-time control. To address this issue, the mechanistic models were used to perform excitation runs and generate data to identify a dynamic, real-time capable Local Linear Model Tree (LOLIMOT) model. This approach was applied to all three process units, and the models' quality was demonstrated by means of experimentally captured data.

关键词： Continuous flow synthesis process modeling Local linear model tree (LOLIMOT) Reaction kinetics advanced process control

来源：评论

学校读者我要写书评

暂无评论

process control in Semiconductor Manufacturing Based on Deep Distributional Soft Actor-Critic Reinforcement Learning

引用

IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING 2025年第2期38卷 210-231页

作者： Liu, Bangxu Zhao, Dewen Lu, Xinchun Liu, Yuhong Tsinghua Univ State Key Lab Tribol Adv Equipment Beijing 100084 Peoples R China

The quality of semiconductor fabrication processes is typically degraded by variations in the manufacturing environment, which can be suppressed by run-to-run (R2R) control schemes. The performance of controlling systems to the produce process which is always highly complex and nonlinear physical model thus is strongly associated with the controlling strategy. However, previous works focusing on less complex semiconductor fabrication processes or linear controlling strategy are both hard to extend the application scenario. A novel structure for a R2R control system based on a distributed form of deep reinforcement learning (DRL), namely, distributional soft actor-critic (DSAC) DRL with twin-value distribution learning, is proposed for multizone pressure control in the chemical mechanical planarization (CMP) process, which is one of the most crucial manufacturing processes for the fabrication of ultra-large integrated circuits (ICs). In addition, several optimization algorithms for DRL, such as twin value distribution learning, are applied, further improving DSAC DRL to enhance the control performance. Compared with other reinforcement learning (RL)-based controllers, the proposed RL control policy achieves better control performance when tested using a multizone CMP virtual metrology (VM) model based on long short-term memory (LSTM) and one-dimensional convolutional neural network (1DCNN) architectures. This deep neural network (DNN) VM model, which is applied for the first time here to test the proposed DRL-based R2R controller for semiconductor manufacturing, is designed to preserve the complexity and nonlinearity of the CMP process by using data recorded from a practical manufacturing process at an IC fabrication facility in Tianjin, China. The novel model-free controlling schemes combined with the new VM model can be used in different R2R application scenarios. Meanwhile the results achieved using the proposed DRL control strategy strongly support its potential

关键词： process control Semiconductor device modeling Semiconductor process modeling Integrated circuit modeling Fabrication Heuristic algorithms Production Adaptation models Training Stability analysis Chemical mechanical planarization advanced process control virtual metrology distributional reinforcement learning soft actor-critic reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Integrated Dynamic Modeling and advanced process control of Carbon Capture Systems 12

Integrated Dynamic Modeling and Advanced Process Control of ...

引用

12th International Conference on Greenhouse Gas control Technologies (GHGT)

作者： Mahapatra, Priyadarshi Ma, Jinliang Ng, Brenda Bhattacharyya, Debangsu Zitney, Stephen E. Miller, David C. Natl Energy Techol Lab Morgantown WV 26507 USA Natl Energy Techol Lab Pittsburgh PA USA Lawrence Livermore Natl Lab Livermore CA USA W Virginia Univ Dept Chem Engn Morgantown WV 26506 USA

Multi-scale dynamic capture models are often too computationally expensive for use in real-time applications, such as operator training and online process control. As a result, innovative methods are required to reduce the complexity of PDE-based and rate-based dynamic models while preserving input-output behavior. In this study, dynamic reduced models (D-RMs) approximate the high-fidelity capture models, thereby offering a trade-off between accuracy, range of applicability, and computational cost. In this paper, we highlight a D-RM builder tool that automatically generates fast D-RMs using pre-computed results from repeated simulation of high-fidelity dynamic process models. Dynamic uncertainty quantification (UQ) analysis is provided that quantifies confidence in the generated D-RM when used as a surrogate 'plant' model. In addition, an advanced process control (APC) framework tool is presented, which uses these reduced-order surrogate models as fast predictive-model(s) for implementing various nonlinear model-predictive control (NMPC) strategies. The developed framework is targeted towards superior disturbance rejection and better responsiveness to demand-changes for otherwise slow capture processes. Published by Elsevier Ltd.

关键词： Dynamic Modeling Reduced-Order Model advanced process control Optimization Carbon Capture MPC CCSI

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：