Intelligent monitoring and control of semiconductor manufacturing equipment
From Semantic Portal Wiki
{{#vardefine:category|Publication}}{{#vardefine:templatename|i.publication}}{{#vardefine:package|smwbp_instance_templates}}
| Edit |
Reference: {{#vardefine:pagename|intelligent monitoring and control of semiconductor manufacturing equipment }}
- [[]]
bibtex
{{#vardefine:pagename|Intelligent monitoring and control of semiconductor manufacturing equipment }}{{#vardefine:key| }}
abstract: This paper describes efforts to apply AI methods to enhance the quality andefficiency of semiconductor manufacturing in a state-of-the-art fabricationdevice called the "rapid thermal multiprocessor(RTM)". Semiconductorfabrication involves many complex processing steps with limited opportunitiesfor measurement of process and product properties. By applying more knowledgeto that limited data, AI monitoring and control methods augment classicalcontrol methods through detection of abnormalities and trends, prediction offailures, diagnosis, planning of corrective action sequences, explanation ofdiagnoses or predictions, and reaction to anomalous conditions that classicalcontrol systems typically would not correct. An architecture for AI controlis described that adapts to complex changing environments such as that foundin fabrication facilities. We illustrate architectural capabilities and ourresearch efforts directed at reasoning about physical components of the RTMwith scenarios from RTM wafer fabrication as well as from our parallel effortin monitoring intensive care patients.
download:
- paper:
- slides:
| Abstract | This paper describes efforts to apply AI m … This paper describes efforts to apply AI methods to enhance the quality andefficiency of semiconductor manufacturing in a state-of-the-art fabricationdevice called the "rapid thermal multiprocessor(RTM)". Semiconductorfabrication involves many complex processing steps with limited opportunitiesfor measurement of process and product properties. By applying more knowledgeto that limited data, AI monitoring and control methods augment classicalcontrol methods through detection of abnormalities and trends, prediction offailures, diagnosis, planning of corrective action sequences, explanation ofdiagnoses or predictions, and reaction to anomalous conditions that classicalcontrol systems typically would not correct. An architecture for AI controlis described that adapts to complex changing environments such as that foundin fabrication facilities. We illustrate architectural capabilities and ourresearch efforts directed at reasoning about physical components of the RTMwith scenarios from RTM wafer fabrication as well as from our parallel effortin monitoring intensive care patients. fortin monitoring intensive care patients. |
| Author | Janet Leeann Murdock +, and Barbara Hayes-Roth + |
| Bibtype | techreport + |
| Institution | Knowledge Systems, AI Laboratory + |
| Key | KSL-91-35 + |
| Month | December + |
| Number | KSL-91-35 + |
| Tag | Computer science + |
| Title | Intelligent Monitoring and Control of Semiconductor Manufacturing Equipment + |
| Tr id | KSL-91-35 + |
| Year | 1991 + |
