Study Of Data Warehouse & Data Mining's Applications In CIMS

In view of Unified Workshop Information System of Fu Jian Oil Refining Company, the application of Data Warehouse and Data Ming is discussed in the framework of CIMS, aided with our research work in these fields. The Main points of this thesis are as follows.1. The development, characters and implement of Data Warehouse are introduced. Fulfilling the requirements of the background project, A design combining OLTP and Data Warehouse are proposed, which can not only satisfy the agility of generating free style reports but also provide a framework for clearing up and synthetically utilizing the raw data.2. Evolutionary algorithms are discussed in the field of Data Mining. We proposed an improved simulated annealing algorithm with neighbor function based on self-optimization of scale parameter. Furthermore incorporating disaster-modification and the improved annealing into genetic algorithm, an Improved genetic-annealing algorithm is proposed. In order to solve the deceptive minimum problem, an improved evolutionary strategy combined with similarity detection and improved mutation operator. Simulation results show the effectiveness of the proposed algorithms.3. Briefly, we introduce the research areas and methods of Data Mining. There are enormous data accumulated accompanying with the application of CIMS. Interested patterns are more imperative in the field of database. A feasible design of Data Mining in the Fu Jian Oil Refining Company is introduced.4. Much more emphasis is put on the skills used during the period of design and implement of the background project, such as Object-Oriented, Unified Modeling Language, Personal Software Process, Team Software Process and Distributed Components. With these aids, the system gets better performance and higher quality.5. Based on the requirements of the background project, information model and function model are designed. The nodi and corresponding solution methods are introduced in detail. The success of the background project approved the rationalities and efficiencies of integrating CIMS with Data Warehouse and Data Mining. Hai Lan(Control Theory & Engineering)Directed by Professor Xiong Wang...