45 KB706 KB41 KB199920252008Imrak, C. Erdem12 straništevilka:2letnik:54str. 103-114ISSN:0039-2480COBISSID:10498331URN:URN:NBN:SI:doc-QEZ9UYBVenAssociation of Mechanical Engineers and Technicians of Slovenia et al.Zveza strojnih inženirjev in tehnikov Slovenije et al.Strojniški vestnikdvigalakontrolni sisteminevronske mrežeArtificial neural networks application in duplex/triplex elevator group control system|Artificial neural networks can offer the better solution to the passenger call distribution problem when compared to the conventional elevator control systems. Therefore, the application of neural networks in elevator group control system is discussed. The significance of introducing artificial neural networks is presented. Elevator group control systems with neural networks can predict the next stopping floors to stop by considering what has been learnt by processing the changes in passenger service demand pattern. This paper deals with the use of artificial neural networks for the distribution of the most suitable cars to the floors by considering the passenger service demand. Artificial neural networks are applied in Duplex/Triplex group control systems for improving passenger waiting time. The back propagation algorithm is used for training neural networks. The elevator traffic analysis and simulation results are presented and compared to conventional elevator control systemsZ umetnimi nevronskimi mrežami lahko, v primerjavi z običajnimi krmiljnimi sistemi dvigal, dobimo boljšo rešitev problema porazdelitve klicev potnikov. Zato v prispevku obravnavamo uporabo nevronskih mrež pri skupinskem sistemu krmiljenja. Predstavljena je smiselnost uvajanja umetnih nevronskih mrež. Skupinski sistem krmiljenja dvigal z nevronskimi mrežami lahko predvidi naslednje nadstropje postanka, z upostevanjem priučenega z obdelavo vzorca sprememb v zahtevah potnikov. V prispevku obravnavamo uporabo umetnih nevronskih mrež za porazdelitev najprimernejših kabin v nadstropja z upoštevanjem zahtev potnikov. Umetne nevronske mreže smo uporabili pri dvojnem/trojnem skupinskem sistemu krmiljenja za zmanjšanje čakalne dobe potnikov. Za učenje nevronskih mrež smo uporabili povratni algoritem. Predstavili smo analizo prometa z dvigali in simulacijo rezultatov ter ju primerjali z običajnim sistemom krmiljenja dvigalTEXTznanstveno časopisjejournalsSlovenian National E-content AggregatorNational and University Library of SloveniaUniverza v Ljubljani, Fakulteta za strojništvo