UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

High capacity bus systems: A design methodology using artificial intelligence

Tyler, NA; (1992) High capacity bus systems: A design methodology using artificial intelligence. Doctoral thesis (Ph.D), UCL (University College London). Green open access

[thumbnail of Tyler_10136543_thesis.pdf]
Preview
Text
Tyler_10136543_thesis.pdf

Download (12MB) | Preview

Abstract

Buses form the basis of the public transport system in many cities of the world: improvements to the operation of bus systems could therefore provide useful benefits in a variety of circumstances. In some cases (notably in Brazil) enhancements to the bus system have been achieved through the design of infrastructure and operations. This study examines both the nature of these enhancements to bus systems and the methods by which they were achieved, in order to facilitate the use of such techniques to improve bus systems elsewhere. Detailed discussions with engineers responsible for existing Brazilian high capacity bus systems reveal how these were conceived and put into operation. In addition, they indicate important variables and models (existing or new) that could be used during this process. In order to distinguish between results obtained on the basis of good quality data and those depending on data of poorer quality, existing artificial intelligence methods are investigated for their performance with poor quality data. These methods may provide some interpretative element, but they do not appear to be appropriate for the representation of the engineer's ability to interpret data. In order to include such assessments, a model is presented which represents the use by the engineer of opinion and judgement in the decision process. The design methodology for high capacity bus systems is represented in a computer model and validated with data representing the situation in a corridor before the implementation of a high capacity bus system. The resulting design is considered to be similar to the design actually implemented. The model is also tested in two other situations where the constraints are more severe, in Peni and in London. The results suggest that it is not possible to obtain a satisfactory design for a high capacity bus system in these corridors.

Type: Thesis (Doctoral)
Qualification: Ph.D
Title: High capacity bus systems: A design methodology using artificial intelligence
Open access status: An open access version is available from UCL Discovery
Language: English
URI: https://discovery.ucl.ac.uk/id/eprint/10136543
Downloads since deposit
175Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item