No description available.

Scheduling trains is a hard problem where current solutions typically create timetables that create undesirable amounts of delay for the trains that use them. This study considers the fact that conventional timetables, which only use fixed intervals to schedule trains, might not be optimal for minimising the delay and travel time of passengers. In this study, we compare this ”simple” timetable with timetables generated via a fuzzy controller which has access to information about the flow of passengers throughout the day. The hypothesis is that this fuzzy controller therefore becomes more ”intelligent”. We evaluate the performance using a custom-built simulator that measures the average delay and travel time of the passengers. We conclude that the fuzzy controller can generate timetables that quickly adapt to passenger demands and show favourable resource usage over the simple timetable. However, more research is needed on the input variables and their usage within the fuzzy controller to further optimise the performance. / Schemaläggning av tåg är ett svårt problem och nuvarande lösningar skapar ofta tidtabeller med oönskade mängder förseningar. Den här rapporten behandlar faktumet att enkla tidtabeller, som enbart använder fasta intervaller för tågens avgång, kanske inte är optimala för att minimera antalet förseningar samt resenärers restid. Den här studien jämför enkla tidtabeller, med fasta intervall, med tidtabeller som skapats av en fuzzy controller som har tillgång till information om passagerarflödet. Hypotesen är att fuzzy controllern på så sätt blir mer intelligent. Rapporten utvärderar hur bra tidtabellerna presterar med hjälp av en simulator som mäter genomsnittlig försening och restid för passagerarna i simulationen. Slutsatsen som dras är att en fuzzy controller kan generera tidtabeller som kan anpassa sig till passagerarflödet samt att denna uppvisar gynnsam resursanvändning i jämförelse med den enkla tidtabellen. Dock framhävs behovet av ytterligare forskning på indatavariabler och dess användning inom fuzzy controllern för att vidare kunna optimera dess prestanda.

Made available in DSpace on 2014-12-17T14:56:21Z (GMT). No. of bitstreams: 1 RafaelBS.pdf: 1607732 bytes, checksum: d5ad875fd4dc09637b9932966f4df8c0 (MD5) Previous issue date: 2003-07-16 / The continuous gas lift method is the main artificial lifting method used in the oil industry for submarine wells, due to its robustness and the large range of flow rate that the well might operate. Nowadays, there is a huge amount of wells producing under this mechanism. This method of elevation has a slow dynamics due to the transients and a correlation between the injected gas rate and the of produced oil rate. Electronics controllers have been used to adjust many parameters of the oil wells and also to improve the efficiency of the gas lift injection system. This paper presents a intelligent control system applied to continuous gas injection in wells, based in production s rules, that has the target of keeping the wells producing during the maximum period of time, in its best operational condition, and doing automatically all necessary adjustments when occurs some disturbance in the system. The author also describes the application of the intelligent control system as a tool to control the flow pressure in the botton of the well (Pwf). In this case, the control system actuates in the surface control valve / O m?todo de eleva??o por g?s lift cont?nuo ? o principal m?todo de eleva??o artificial utilizado, principalmente, para produ??o em po?os submarinos devido a sua robustez e a larga faixa de vaz?o que o po?o pode produzir. H? um grande percentual de po?os produzindo sob este mecanismo no Brasil. Este tipo de m?todo de eleva??o apresenta algumas caracter?sticas pr?prias, sendo uma delas sua din?mica lenta devido aos transientes e outra ? a exist?ncia de uma correla??o entre a vaz?o de g?s injetado e a vaz?o de ?leo produzido. Controladores eletr?nicos t?m sido utilizados para realizar ajustes em alguns par?metros do po?o e melhorar a efici?ncia de inje??o de g?s lift. Este trabalho apresenta um sistema inteligente de controle autom?tico da inje??o de g?s, baseando-se em regras de produ??o, que busca manter os po?os equipados para g?s lift cont?nuo produzindo o maior tempo poss?vel, nas condi??es ?timas de opera??o e que faz os ajustes autom?ticos necess?rios quando ocorre alguma perturba??o no sistema. Mostra-se que ? poss?vel, utilizando o sistema inteligente apresentado, exercer o controle da press?o de fluxo no fundo do po?o (Pwf) atrav?s da manipula??o da abertura da v?lvula de controle de superf?cie