An Artificial neural network approach for process variance change detection for both small and large shifts
(2010) STAM01 20101Department of Statistics
- Abstract
- Nowadays Statistical process control charts (SPCC) has become powerful tools to monitor process variability of products in manufacturing environments. The artificial neural network (ANN) technique is also nowadays popular to use for monitoring process variability of products as an alternative to SPCC due to its superior performance. This research focus on the ANN technique for monitoring the process variance. We describe the ANN approach to monitor process variance change and shows that it is more efficient than traditional statistical control charts (R charts and EWMA charts) for both small and large shifts. The performance of the proposed scheme (ANN) is compared to SPCC for samples of size five in terms of average run length to... (More)
- Nowadays Statistical process control charts (SPCC) has become powerful tools to monitor process variability of products in manufacturing environments. The artificial neural network (ANN) technique is also nowadays popular to use for monitoring process variability of products as an alternative to SPCC due to its superior performance. This research focus on the ANN technique for monitoring the process variance. We describe the ANN approach to monitor process variance change and shows that it is more efficient than traditional statistical control charts (R charts and EWMA charts) for both small and large shifts. The performance of the proposed scheme (ANN) is compared to SPCC for samples of size five in terms of average run length to detection of change. The robustness of the proposed scheme (ANN) is also examined. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/1614352
- author
- Zaman, Babar LU
- supervisor
- organization
- course
- STAM01 20101
- year
- 2010
- type
- H1 - Master's Degree (One Year)
- subject
- keywords
- Artificial Neural Network for process control
- language
- English
- id
- 1614352
- date added to LUP
- 2010-06-21 12:12:53
- date last changed
- 2010-06-21 12:12:53
@misc{1614352, abstract = {{Nowadays Statistical process control charts (SPCC) has become powerful tools to monitor process variability of products in manufacturing environments. The artificial neural network (ANN) technique is also nowadays popular to use for monitoring process variability of products as an alternative to SPCC due to its superior performance. This research focus on the ANN technique for monitoring the process variance. We describe the ANN approach to monitor process variance change and shows that it is more efficient than traditional statistical control charts (R charts and EWMA charts) for both small and large shifts. The performance of the proposed scheme (ANN) is compared to SPCC for samples of size five in terms of average run length to detection of change. The robustness of the proposed scheme (ANN) is also examined.}}, author = {{Zaman, Babar}}, language = {{eng}}, note = {{Student Paper}}, title = {{An Artificial neural network approach for process variance change detection for both small and large shifts}}, year = {{2010}}, }