You are here
Integrating Multiobjective Optimization with the Six Sigma Methodology for Online Process Control
- Date Issued:
- 2013
- Abstract/Description:
- Over the past two decades, the Define-Measure-Analyze-Improve-Control (DMAIC) framework of the Six Sigma methodology and a host of statistical tools have been brought to bear on process improvement efforts in today's businesses. However, a major challenge of implementing the Six Sigma methodology is maintaining the process improvements and providing real-time performance feedback and control after solutions are implemented, especially in the presence of multiple process performance objectives. The consideration of a multiplicity of objectives in business and process improvement is commonplace and, quite frankly, necessary. However, balancing the collection of objectives is challenging as the objectives are inextricably linked, and, oftentimes, in conflict.Previous studies have reported varied success in enhancing the Six Sigma methodology by integrating optimization methods in order to reduce variability. These studies focus these enhancements primarily within the Improve phase of the Six Sigma methodology, optimizing a single objective. The current research and practice of using the Six Sigma methodology and optimization methods do little to address the real-time feedback and control for online process control in the case of multiple objectives.This research proposes an innovative integrated Six Sigma multiobjective optimization (SSMO) approach for online process control. It integrates the Six Sigma DMAIC framework with a nature-inspired optimization procedure that iteratively perturbs a set of decision variables providing feedback to the online process, eventually converging to a set of tradeoff process configurations that improves and maintains process stability. For proof of concept, the approach is applied to a general business process model (-) a well-known inventory management model (-) that is formally defined and specifies various process costs as objective functions. The proposed SSMO approach and the business process model are programmed and incorporated into a software platform. Computational experiments are performed using both three sigma (3?)-based and six sigma (6?)-based process control, and the results reveal that the proposed SSMO approach performs far better than the traditional approaches in improving the stability of the process. This research investigation shows that the benefits of enhancing the Six Sigma method for multiobjective optimization and for online process control are immense.
Title: | Integrating Multiobjective Optimization with the Six Sigma Methodology for Online Process Control. |
52 views
17 downloads |
---|---|---|
Name(s): |
Abualsauod, Emad, Author Geiger, Christopher, Committee Chair Elshennawy, Ahmad, Committee Member Thompson, William, Committee Member Moore, Karla, Committee Member , Committee Member University of Central Florida, Degree Grantor |
|
Type of Resource: | text | |
Date Issued: | 2013 | |
Publisher: | University of Central Florida | |
Language(s): | English | |
Abstract/Description: | Over the past two decades, the Define-Measure-Analyze-Improve-Control (DMAIC) framework of the Six Sigma methodology and a host of statistical tools have been brought to bear on process improvement efforts in today's businesses. However, a major challenge of implementing the Six Sigma methodology is maintaining the process improvements and providing real-time performance feedback and control after solutions are implemented, especially in the presence of multiple process performance objectives. The consideration of a multiplicity of objectives in business and process improvement is commonplace and, quite frankly, necessary. However, balancing the collection of objectives is challenging as the objectives are inextricably linked, and, oftentimes, in conflict.Previous studies have reported varied success in enhancing the Six Sigma methodology by integrating optimization methods in order to reduce variability. These studies focus these enhancements primarily within the Improve phase of the Six Sigma methodology, optimizing a single objective. The current research and practice of using the Six Sigma methodology and optimization methods do little to address the real-time feedback and control for online process control in the case of multiple objectives.This research proposes an innovative integrated Six Sigma multiobjective optimization (SSMO) approach for online process control. It integrates the Six Sigma DMAIC framework with a nature-inspired optimization procedure that iteratively perturbs a set of decision variables providing feedback to the online process, eventually converging to a set of tradeoff process configurations that improves and maintains process stability. For proof of concept, the approach is applied to a general business process model (-) a well-known inventory management model (-) that is formally defined and specifies various process costs as objective functions. The proposed SSMO approach and the business process model are programmed and incorporated into a software platform. Computational experiments are performed using both three sigma (3?)-based and six sigma (6?)-based process control, and the results reveal that the proposed SSMO approach performs far better than the traditional approaches in improving the stability of the process. This research investigation shows that the benefits of enhancing the Six Sigma method for multiobjective optimization and for online process control are immense. | |
Identifier: | CFE0004968 (IID), ucf:49561 (fedora) | |
Note(s): |
2013-12-01 Ph.D. Engineering and Computer Science, Industrial Engineering and Management Systems Doctoral This record was generated from author submitted information. |
|
Subject(s): | Six Sigma -- multiobjective optimization -- online process control | |
Persistent Link to This Record: | http://purl.flvc.org/ucf/fd/CFE0004968 | |
Restrictions on Access: | public 2013-12-15 | |
Host Institution: | UCF |