Data Mining System Based On Process Monitoring And Control And Its Application

With the development of automation and the high demand of reliableness and safety in modern industrial production, process monitoring and control has become one of the important researching directions in process automation. The theory and practice of process monitoring and control involves in many subjects and technologies, but it is still a hard and hot research direction in process fault inspection and getting fault diagnosis rules. So we research mainly on industrial process fault diagnosis. With the development of computer and network, the collected data in fault diagnosis is increasing rapidly, so we can apply data mining technology to fault diagnosis.Therefore, we propose the data mining system based on fault diagnosis. The data mining system based on fault diagnosis is a data mining system designed on the particularity of fault diagnosis.Rough set is the key technology of the system. The data collected from reality often contain noisy, uncertainty, and incompleteness. It is not ideal when supposing with pure mathematics to eliminate uncertainty. Rough set as a classify theory of data mining is a strong mathematic tool dealing with uncertainty and incompleteness, and it is a new researching direction in fault diagnosis. Rough set as a classify theory of data mining can get useful knowledge from huge data, so it can apply in fault diagnosis effectively, and it can overcome the difficulty in getting knowledge existed before.When designing the algorithm, we think of the particularity of the dataand the demand in fault diagnosis. We propose an data mining algorithm based on rough set and a method transfering tense information system to information system.Database connection pool technology is used in the system. It can reuse the resource that occupies the memory as much as possible, so the efficiency of the programme will improve. At the same time, it can monitor the connection amount and use by its own management system.The system using rough set as its key technology and choosing suitable algorithm, can deal with uncertainty. It can work out the fault diagnosis rules rapidly.This dissertation discusses rough set theory related, proposes concrete algorithm, and introduces the structure and function of the data mining system based on fault diagnosis. Finally, the dissertation introduces an application of the system.Xin Xu-ming(Control Theory and Control Engineering) Supervised by-Associate Professor Sun Fu-liang...