Study Of Case Based Reasoning And Application In Runout Table Cooling Process

Case Based Reasoning(CBR)has become one of the novel important reasoning ways because of its flexible approaches of reasoning, high efficient and intelligent reasoning mechanism and so on. It is able to solve new problems based on specific past knowledge and shows advantages over conventional expert systems when there is only experience and no explicit model. The runout table cooling process is used to control the strip from the finishing temperature to the coiling temperature and obtain products with good properties. It is difficult to determine parameters such as the heat transfer coefficient and the thermal conductivity of the runout table cooling process because of its complex nature (e.g., highly nonlinear, time varying). In view of the above questions, this thesis presents the application research of case based reasoning in the runout table cooling process based on the extensive survey of the current research situation of case based reasoning.The main contributions of the thesis are as follows:The current development of case-based reasoning, including the subtasks of case representation, case retrieval, case reuse, case revision, case retention , and case base maintenance and its application, is presented through the analysis and discussion of the extensive literature, and an overview of the case based reasoning process is given.The heat transfer coefficient and the thermal conductivity during the runout table cooling process are determined, by layered case retrieval. After the analysis of the cases features, the feature similarity is divided into some levels and simulation experiments are made using the software MATLAB for programming. Based on the model experiment results with various steel grades under various conditions confirm that the method to determine the heat transfer coefficient and the thermal conductivity is effective.