The Mass Rapid Transit (MRT) systems have been built in many metropolitans to solve the public transportation problem such as traffic congestion. With such high investment cost, it is important to design a proper operation strategy to reduce the operational cost which achieving the system performance. With less ridership as compared to Taipei MRT system, the minimization of social cost which consists of energy consumption and the traveling time to complete the journey, has been investigated for Kaohsiung MRT (KMRT) system. By this way, the optimal coasting speed between train stations is solved according to the ridership and distance between the
stations.
The artificial neural network (ANN) has proposed in this
thesis to determine the optimal coasting speed of the train set. The energy consumption and the traveling time to complete the journey between stations with various riderships are calculated by exactly the train performance simulation to generate the training data set. The objective function is defined by considering the energy consumption and the traveling time cost of passengers. By performing the ANN training, the ANN model is therefore obtained, which can be used to solve the optimal coasting speed of train sets. To demonstrate the effectiveness of the proposed ANN model, the forecasting of annual ridership for both Orange Line and Red Line of KMRT
system is used. The optimal coasting speed and the corresponding profile of power consumption have been solved
to minimize the social cost of MRT systems operation.
| Identifer | oai:union.ndltd.org:NSYSU/oai:NSYSU:etd-0709106-154058 |
| Date | 09 July 2006 |
| Creators | Hsieh, Ching-Ho |
| Contributors | Chen-Chiu Chang, Hui-Jen Chuang, Tsai-Hsiang Chen, Chao-Shun Chen |
| Publisher | NSYSU |
| Source Sets | NSYSU Electronic Thesis and Dissertation Archive |
| Language | Cholon |
| Detected Language | English |
| Type | text |
| Format | application/pdf |
| Source | http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0709106-154058 |
| Rights | campus_withheld, Copyright information available at source archive |
Page generated in 0.0024 seconds