The recent downturn in world sugar prices has placed even greater demands upon the Australian sugar industry to reduce the costs of sugar manufacture and increase the consistency of producing high quality sugar. One of the proposed approaches in increasing the consistency of very high quality sugar production and leveraging further avenues for cost saving is in the development of a computer based advisory system. This system is able to provide expert knowledge in the area of pan stage management and best practices in the absence of human experts. This thesis explores the design, key features and outcomes of a knowledge based supervisory support system (KBSSS) framework proposed specifically for providing cooperative decision support in the area of pan stage operations within a sugar mill. To demonstrate the viability of the proposed KBSSS framework a prototype system was developed in accordance with the proposed framework. The KBSSS utilises three core innovative system technologies that form the core components of the proposed KBSSS framework. These technologies are: 1) Dynamic industrial pan stage process models for identifying the dynamic relationships between sections of pan stage operations to allow for future forecasting of pan stage operating conditions, 2) Integration techniques for the merging of the developed pan stage process models into the hybrid fuzzy logic expert system rule base to provide localisation adjustment to match with local real world factory operational conditions, and 3) Explanatory capabilities to provide justification and support of system advice and recommendations. As a result of research and development carried out in this thesis, the KBSSS's test results demonstrated in the thesis indicate the viability of the proposed KBSSS framework and highlight the forecasting capabilities of the developed system resulting in favourable outcomes compared to data from pan stage operations. As a result of the research undertaken in the thesis a prototype KBSSS, for pan stage operations, based upon the three core supporting intelligent system technologies reported in the thesis has been developed.
| Identifer | oai:union.ndltd.org:ADTP/241366 |
| Date | January 2009 |
| Creators | Dodd, Roland John, roland.dodd@gmail.com |
| Publisher | RMIT University. Electrical and Computer Engineering |
| Source Sets | Australiasian Digital Theses Program |
| Language | English |
| Detected Language | English |
| Rights | http://www.rmit.edu.au/help/disclaimer, Copyright Roland John Dodd |
Page generated in 0.0076 seconds