基于粗糙集-思维进化算法的应用研究-控制理论与控制工程专业论文.docxVIP

太累理工大学峡士研究生学位论文 RESEARCHANDAPPLICAτION BASED ON ROUGH SETS AND MEA ABSTRACT This paper deeply analyzes basic ideas and pi出 of Rough Set theory， introduces its ∞mbination with other 80ft ∞mputing methods such as evolution algorithms，fuzzy sets，neural networks，and then reviews its current application in Intelligent Control systems. Rough Set th∞，ry method 扭alyzes l?mited-dimension discrete datasheet，so we must discretize data in database. But for an original database with laτge continuous at挝butes values，how 10 discretize data reasonably is a noticeatle probl钮L Aiming at 也包 condition，by using the characteristics of rough set which can explore kno何ledge from data and mind evolutionary algorithm which can find 技le best point global忡， this paper combines the two methods for the first time，and used mind evolutionary algorithm 10 search reasonable split points. C白nsidering the whole condition attrib鼠目val口目， 往lis paper proposes a global discretization approach to avoid creating unreasonable dìscrete split points 也at appe缸ed in discretizing each 4 太原理工大学!i9l士研究生学位论文 continuous at位ibute independently. By using 也eme让lO d in 也IS pap眩，也z input 扭d output data of cement stove were analyzed ，and the fuzzy model of c四lent stove is establishedτhe experiment shows that the method ?s simple and rapid andωn elide complex handwork reduction. Applying 面s method into the ∞mplex controlled object with lar亘古 time delay and characteristic of time v部yi吨， a fuzzy ∞ntroller based on rough set and mind evolutionary a1gori也m is presented in this paper. By studying input and output characters of the controlled object ，which is under the control of experts，rough set and 泣le mind evolutionary a1gorilhm together provide an efficient method to convert expert knowledge 企om data 10 fuzzy rules. This method will largely enhance the MIQ of the intellig吉nt system. KEYWORDS: Tough sets，information quantity，mind evolutionary a1gorithm，fuzzy modeling 5 太原理工大学硕士研究生学位论文 图表索