Home >>> Tutorial
Tutorial
In addition to the conference, three technical Tutorials will take place on Monday, March, 31 in the morning.
The Tutorial is organized by Prof. Dr. Johann W. Bartha, University of Dresden.
8:00 - 8:30 |
Tutorial Registration |
8:30 - 12:30 |
Tutorial 1:
"General Introduction of APC"
Presenter: James Moyne (Applied Materials / University of Michigan), Martin Schellenberger (Fraunhofer Institute IISB)
|
Tutorial 2:
"Insight into a Factory-Wide Process Control System"
Presenter: Roland Willmann
CEO of CenterPoint
|
Tutorial 3:
"Machine Learning and Data Mining for Industrial Applications – from Theory to Practice"
Presenter: Dr. Boaz Lerner
Department of Industrial Engineering & Management
Ben-Gurion University, Israel
|
| Tutorial 1: "General Introduction of APC" |
| Outline |
| |
The Tutorial discusses advanced process control approaches to gain higher manufacturing flexibility on a factory-wide level, driven by the need to increased product mix, cost-pressure and technology complexity.
Different disciplines are integrated to a comprehensive picture. Learn about data collection, the integration of process control data and quality control data, integration between model tuning and model adoption, abstraction of the manufacturing process, prediction techniques and much more. |
| Presenter |
Ariel Greisas
(Intel)
|
Ariel Greisas has joined Intel in 2000 and is currently working in Fab28 automation department, responsible for the development and deployment of advanced process control solutions for various process areas, such as Litho, Planar, Metro and others.
Over the years, he has been part of development and implementation of various Eng Analysis systems for different Intel sites, mainly in the Defect Metrology and Litho areas, and is currently active in the fields of Advanced Process Control, Adaptive Sampling and Excursion Prevention.
Ariel is holding a Bachelor degree in Chemical Engineering from Ben Gurion University in Be'er Sheva, Israel.
He can be reached at ariel.greisas ( at ) intel.com
|
James Moyne
(Univ. of Michigan) |
James Moyne is Director of Advanced Process Control Technology for Brooks Automation.
He received his B.S.E.E. and B.S.E. - Mathematics, and his M.S.E.E. and Ph.D. degrees from the University of Michigan, where he is currently an Associate Research Scientist in the Department of Electrical Engineering and Computer Science.
Dr. Moyne was president and co-founder of MiTeX Solutions, Inc., established in 1995 to provide maintainable and configurable run-to-run control solutions for semiconductor and display manufacturing; MiTeX Solutions was purchased by Brooks Automation in 2000.
Dr. Moyne has experience in advanced process control, database technology, and sensor bus technology, and is the author of a number of many refereed publications in each of these areas. He also holds the patent on a software control framework enabling technology called the Generic Cell Controller, and is co-author of Run-to-run Control in Semiconductor Manufacturing. He is also the author of a number of SEMI standards in the areas of process control, sensor bus, and communications, and currently co-chairs process control systems and sensor bus standards efforts.
|
Martin Schellenberger
(FhG IISB) |
Martin Schellenberger joined the department of Semiconductor Manufacturing Equipment and Methods at the Fraunhofer Institute of Integrated Circuits and Device Technology (IISB) in 1998. He is responsible for the development of solutions for integrated metrology and their link to advanced process control systems.
He is active in the fields of software architectures for the integration of metrology and sensors, interfaces and protocols for equipment communication in semiconductor manufacturing, internet communication and eDiagnostics as well as cluster processing for new materials.
Martin received his diploma in Electrical Engineering in 1998 from the University of Erlangen-Nuremberg, Germany.
He can be reached at martin.schellenberger ( at ) iisb.fraunhofer.de. |
| Tutorial 2: "Insight into a Factory-Wide Process Control System" |
| Outline |
| |
Summary: The tutorial discusses advanced process control approaches to gain higher manufacturing flexibility on a factory-wide level, driven by the need for increased product mix, cost-pressure and technology complexity, based on R&D experiences in cooperation with semiconductor manufacturers.
The tutorial leads in a picture of collected data, the condensation, correlation and classification of data, the definition of automated decision making rules and prediction techniques as a comprehensive concept for a living corporate knowledge repository in a factory-wide software-infrastructure.
The tutorial integrates multiple disciplines and techniques to a overall picture of continuous improvement and execution of APC scenarios on the single process-level and the factory-level as well. The contents in detail are dynamic data collection, the mapping to a logical process view, data-mining techniques, the integration of process control data and quality control data and the integration between model-tuning and model-adoption during volume production. |
| Presenter |
Roland Willmann
(CenterPoint) |
Roland Willmann
CEO of CenterPoint – Connective Software Engineering GmbH
Holding a Master in Software Engineering of the Technical University of Vienna.
He was involved in several Software Projects of the Semiconductor Industry between 1990 and 2000.
Since 2000 he is co-founder, CEO and Technical Director of CenterPoint – Connective Software Engineering GmbH in Villach/Austria.
Roland Willmann was also the European Co-chair of the SEMI EDA Taskforce for the development of new e-Manufacturing standards.
|
| Tutorial 3: "Machine Learning and Data Mining for Industrial Applications – from Theory to Practice" |
| Outline |
| |
The performance of a machine learning model is improved by updating (learning) the model parameters through experience and use of the data. This improvement can be manifested, for example, in higher accuracy, lower computational complexity or reduced use of resources. Machine learning models find application in data mining, decision making and the detection, classification, prediction, compression and representation of data. Moreover, machine learning allows natural incorporation of application knowledge into a data-driven model in order to select a better model or improve the estimation of its data-driven parameters. Machine learning and data mining models have proved their accuracy, stability and reliability in an ever-increasing variety of industrial applications.
The proposed "Machine Learning and Data Mining for Industrial Applications – from Theory to Practice" short course is offered to engineers and researchers in the semiconductor industry. The purpose of the course is to advance the theoretical and practical knowledge necessary for accelerating the development and use of more intelligent and more efficient tools in automatic equipment and process control. The course is designed to bridge the gap between the state-of-the-art knowledge that has been accumulated in the machine learning and data mining communities and the growing need to find more intelligent and efficient solutions to complex industrial problems. This need increases with the technological level of the application, the complexity of the equipment/process, the requirements from the equipment/process, the number of variables/parameters involved and the amount of data available.
In this short self-contained course, we will provide a graduate-level introduction to the field of machine learning. We will present the principles of machine learning and data mining and will focus on successful machine learning methods. We will provide an understanding of the differences between the various methods and their pros and cons, and of the tools needed for selecting the relevant method for a particular problem. Finally, we will demonstrate advanced developments and applications of machine learning methods in the industry. |
| Presenter |
Boaz Lerner
Ben-Gurion University |
Dr. Boaz Lerner
Department of Industrial Engineering & Management
Ben-Gurion University, Israel
boaz ( at ) bgu.ac.il
http://www.ee.bgu.ac.il/~boaz/
Boaz Lerner received the B.A. degree in Physics and Mathematics from the Hebrew University, Israel, in 1982 and the Ph.D. degree in Computer Engineering from Ben-Gurion University, Israel, in 1996.
Dr. Lerner performed research at the Neural Computing Research Group at Aston University, Birmingham, U.K. and the Computer Laboratory of the University of Cambridge, Cambridge, U.K.
In 2000 he joined Ben-Gurion University, Israel, where he is currently a Senior Lecturer at the Department of Industrial Engineering & Management.
His current interests include machine learning and data mining and their applications in the industry.
|
Tutorial Contact
Johann W. Bartha
bartha ( at ) ihm.et.tu-dresden.de
|
Contact
Gitta Haupold
haupold ( at ) aecapc-europe.com
|
|
