الفهرس 
introductionOnly 14 pages are availabe for public view
 |  | from | 16 |  |  |
| | | from | 16 | | |
Abstract
thesis presents new modifications on Genetic Algorithm (GAs) teclmique for Genetic-Fuzzy controller (GFC) system to obtain faster operations, more efficient perlilllnance, and oplinn”n ~;olution wilhin n limiled I1IlIIlher 01” genellltio!t<;. lhe modified Genetic technique mainly depends on dividing the chromosome length of the GAs into two equal Bisections Genetic AI!,>orithms (BGA) to improve the optimization prohahility and calc.hing Ihe slmllgesl fitness of Ihe BGA 10 avoid losing il. M:my simulations are applied to study and analyze the advantages of the Bisections Genetic¬Fuzzy Controller (BGFC) system and to conclude its criteria. Two different applications are used to show the versatility of the BGFC system over the Simple Genetic-Fuzzy controller (SGFC) system in industry. The applications results show that the introduced BGFC system is much faster and has better performance than the normal procedure system. 111e presented thesis consists of seven chapters.
lhe filsl chaplct plcscnts an introduction 10 aulomatic control principles, concepts, and design. Also, it explains conventional control theory and its methodology for designing and adjusting automatic control devices. Then it prescnls the cxpert systcms rUid its technology, plel1lises, and npplicahilily 10 aulol1lalic conllol process.
The second chapter presents an introduction to Fuzzy Logic Control (FLC) features, foundations, and IF-11IEN rules. it also illustrates its types of membership fimctions (MFs). ll1en, it presents Mamdani FLC model which is a famous controller type, Fuzzification, fuzzy operation, and implication method, and defuzzjfication are mentioned as m~or steps of Mamadani FLC.
’111e third chapter pH.-sents ill! introduction to genetic algorithms (Gas) technique, features, and operations. It also illustrates a comparison between GAs and the traditional I methods for optimization. Initiali7.ation, fitness-calculation, reproduction, crossovet and
l11utalion arc prescnts l~xplaill(’d as l1Iajm steps of Sil1lpl” (Jelldic AI,~OI ithllls (S
fourth chapter presents an introduction to Genetic-Fuzzy controller (GFC) system. It also illustrates how Simple Genetic Algorithms (SGA) used as an optimization technique to obtain the unknown FLC membership functions for Simple Genetic-Fuzzy controllcr (S( jF( ’) simulation syslem II presents a stndy /(11’ the simnlation results curve wid analysis li.)r thc rcasons or,hc systcm prohk’ms.
’IIII’ fillh •. hapkl illllodlln”; lIi~”’dioll (;(’lIdi(” AI,~OI ill 1111’; (II( iA) w; II ’”odili(’{1 technique lor Simple Uenetic Algorithms (SUA). It explains the design of the Bisection Genetic Fuzzy Controller (BGFC) system To study the advantages of the BGA technique over that of the SGA technique, different cases of chromosome lengths are tested for both techniques. ”The results prove that the BGFC is faster and has a better performance than theSGFC.
’f11e sixth chapter presents an introduction to the cemenl industry aJld discussing Ihc kiln plOcess ’1 hc ”wning systcm and kiln spccd or cemcnl kiln opcmlion m(~ discussed as two dillerent applications for Uenetic-Fuzzy system. ’f1le designing sleps of the fuzzy controller are driven. lhen BOA is applied :JS an optimizer method for fuz.zy
which are reviewed by production’s experts and compared with the data sheets and curves proves that the BGFC obtains faster operations, more efficient performance, and optimum solution within a limited number of generations than the SGFC.
The seventh chapter gives a conclusion for the thesis and analysis for its results. It also explains main idea of the snggesled fnture works.