Diagnosing manufacturing process variation using higher order statistics : a blind source separation approach /
A large volume of multivariate data is available from the manufacturing process. A new statistical approach in the context of signal processing is investigated to diagnose the root causes of unusual variability from the multivariate measurement data. Since the existing statistical approaches, which...
| Main Author: | |
|---|---|
| Format: | Thesis eBook |
| Language: | English |
| Published: |
[Place of publication not identified] :
[publisher not identified] ;
2000.
|
| Subjects: | |
| Online Access: | Link to OAKTrust copy |
| Summary: | A large volume of multivariate data is available from the manufacturing process. A new statistical approach in the context of signal processing is investigated to diagnose the root causes of unusual variability from the multivariate measurement data. Since the existing statistical approaches, which are related to the process diagnosis and uses second order statistic, have limitations and restrictions, the new statistical approach uses higher order information. The new approach is analyzed in several situations and is compared with one of existing statistical approach. For example, autobody assembly process is used. |
|---|---|
| Item Description: | "Major subject: Industrial Engineering". Vita. |
| Physical Description: | ix, 59 leaves : illustrations ; 28 cm. Also available online. Issued also on microfiche from Lange Micrographics. |
| Bibliography: | Includes bibliographical references (leaves 53-56). |