Using causal knowledge to improve retrieval and adaptation in case-based reasoning systems for a dynamic industrial process.
Date of Award
CC BY-NC-ND 4.0
Case-based reasoning (CBR) is a reasoning paradigm that starts the reasoning process by examining past similar experiences. The motivation behind this thesis lies in the observation that causal knowledge can guide case-based reasoning in dealing with large and complex systems as it guides humans. In this thesis, case-bases used for reasoning about processes where each case consists of a temporal sequence are considered. In general, these temporal sequences include persistent and transitory (non-persistent) attributes. As these sequences tend to be long, it is unlikely to find a single case in the case-base that closely matches the problem case. By utilizing causal knowledge in the form of a dynamic Bayesian network (DBN) and exploiting the independence implied by the structure of the network and known attributes, this system matches independent portions of the problem case to corresponding sub-cases from the case-base. However, the matching of sub-cases has to take into account the persistence properties of attributes. The approach is then applied to a real life temporal process situation involving an automotive curing oven, in which a vehicle moves through stages within the oven to satisfy some thermodynamic relationships and requirements that change from stage to stage. In addition, testing has been conducted using data randomly generated from known causal networks. (Abstract shortened by UMI.) Paper copy at Leddy Library: Theses & Major Papers - Basement, West Bldg. / Call Number: Thesis2005 .T54. Source: Masters Abstracts International, Volume: 45-01, page: 0366. Thesis (M.Sc.)--University of Windsor (Canada), 2006.
Tighe, Christopher A., "Using causal knowledge to improve retrieval and adaptation in case-based reasoning systems for a dynamic industrial process." (2006). Electronic Theses and Dissertations. 4482.