Intelligent elevator control based on adaptive learning and optimisation

• Main Author: Jordaan, Edzard Adolf Biermann
• Other Authors: Randewijk, Peter Jan
• Format: Others
• Language: en_ZA
• Published: Stellenbosch : Stellenbosch University 2015
• Subjects: Intelligent control systems; Machine learning; Artificial intelligence > Industrial applications; Elevators > Computer programs; Theses > Electronic engineering; Dissertations > Electronic engineering; UCTD
• Online Access: http://hdl.handle.net/10019.1/95999

Thesis (MEng)--Stellenbosch University, 2014. === ENGLISH ABSTRACT: Machine learning techniques have been around for a few decades now and are being established as a pre-dominant feature in most control applications. Elevators create a unique control application where traffic flow is controlled and directed according to certain control philosophies. Machine learning techniques can be implemented to predict and control every possible traffic flow scenario and deliver the best possible solution. Various techniques will be implemented in the elevator application in an attempt to establish a degree of artificial intelligence in the decision making process and to be able to have increased interaction with the passengers at all times. The primary objective for this thesis is to investigate the potential of machine learning solutions and the relevancy of such technologies in elevator control applications. The aim is to establish how the research field of machine learning, specifically neural network science, can be successfully utilised with the goal of creating an artificial intelligent (AI) controller. The AI controller is to adapt to its existing state and change its control parameters as required without the intervention of the user. The secondary objective for this thesis is to develop an elevator model that represents every aspect of the real-world application. The purpose of the model is to improve the accuracy of existing theoretical and simulated models, by modulating previously unknown and complex variables and constraints. The aim is to create a complete and fully functional testing platform for developing new elevator control philosophies and testing new elevator control mechanisms. To achieve these objectives, the main focus is directed to how waiting time, probability theory and power consumption predictions can be optimally utilised by means of machine learning solutions. The theoretical background is provided for these concepts and how each subject can potentially influence the decision making process. The reason why this approach has been difficult to implement in the past, is possibly mainly due to the lack of adequate representation for these concepts in an online environment without the continuous feedback from an Expert System. As a result of this thesis, the respective online models for each of these concepts were successfully developed in order to deal with the identified shortcomings. The developed online models for projected waiting times, probability networks and power consumption feedback were then combined to form a new Intelligent Elevator Controller (IEC) structure as opposed to the Expert System approach, mostly used in present computer based elevator controllers. === AFRIKAANSE OPSOMMING: Masjienleertegnieke bestaan al vir 'n paar dekades en is 'n oorwegende kenmerk in hedendaagse beheertoestelle. Hysbakke skep 'n unieke beheertoepassing, waar verkeersvloei beheer en gerig kan word volgens sekere beheer loso e. Masjienleertegnieke kan geïmplementeer word om elke moontlike verkeersvloei situasie te voorspel en te beheer en die beste moontlike oplossing te lewer. Verskeie tegnieke sal in die tesis ondersoek word in 'n poging om 'n mate van kunsmatige intelligensie in die besluitneming proses te skep asook verhoogte interaksie met die passasiers te alle tye. Die prim^ere doel van hierdie tesis is om die potensiaal van 'n masjienleer oplossing en die toepaslikheid van dit in hysbakbeheertoepassings te ondersoek. Die doel is om vas te stel hoe die navorsing in die veld van die masjienleer, spesi ek in neurale netwerk wetenskappe, suksesvol aangewend kan word met die doel om 'n kunsmatige intelligente beheerder te skep. Die kunsmatige intelligente beheerder moet kan aanpas by sy onmidelike omgewing en sy beheer parameters moet kan verander soos nodig sonder die ingryping van die gebruiker. Die sekond^ere doelwit vir hierdie tesis is om 'n hysbakmodel, wat elke aspek van die werklike w^ereld verteenwoordig, te ontwikkel. Die doel van die model is om die akkuraatheid van die bestaande teoretiese en gesimuleerde modelle te verbeter deur voorheen onbekende en komplekse veranderlikes en beperkings in ag te neem. Die doel is om 'n funksionele toetsplatform te skep vir die ontwikkeling van nuwe hysbakbeheer loso e en vir die toets van nuwe hysbakbeheermeganismes. Om hierdie doelwitte te bereik, is die hoo okus gerig om wagtyd, waarskynlikheidsteorie en kragverbruik voorspellings optimaal te gebruik deur middel van die masjienleer oplossings. Die teoretiese agtergrond is voorsien vir hierdie konsepte en hoe elke konsep potensieel die besluitneming kan beïnvloed. Die rede waarom hierdie benadering moeilik was om te implementeer tot hede, is moontlik te wyte aan die gebrek aan voldoende verteenwoordiging vir hierdie konsepte in 'n aanlynomgewing sonder die voortdurende terugvoer van 'n Deskundige Stelsel. As gevolg van hierdie tesis word die onderskeie aanlynmodelle vir elk van hierdie konsepte suksesvol ontwikkel om die geïdenti seerde tekortkominge te oorkom. Die ontwikkelde aanlynmodelle vir geprojekteerde wagtye, waarskynlikheidsnetwerke en kragverbruik terugvoer is dan gekombineer om 'n nuwe intelligente hysbakbeheerder struktuur te skep, in teenstelling met die Deskundige Stelsel benadering in die huidige rekenaar gebaseerde hysbakbeheerders.