Improvement of traffic flow management at intersections using cluster analysis and fuzzy logic
Signal-controlled intersections of urban transport highways are the busiest and most problematic places in the urban road network because of vehicle delays at intersections reducing their traffic capacity, as well as a sharp change in the nature of traffic (braking-waiting-acceleration), which worse...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Belgrade - Faculty of Mechanical Engineering, Belgrade
2025-01-01
|
| Series: | FME Transactions |
| Subjects: | |
| Online Access: | https://scindeks-clanci.ceon.rs/data/pdf/1451-2092/2025/1451-20922503499S.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Signal-controlled intersections of urban transport highways are the busiest and most problematic places in the urban road network because of vehicle delays at intersections reducing their traffic capacity, as well as a sharp change in the nature of traffic (braking-waiting-acceleration), which worsens the environmental situation. This paper develops a mathematical model for calculating the recommended vehicle speed at signal-controlled intersections for non-stop passage, in order to increase the traffic capacity and safety, taking into account various factors. The authors carry out a preliminary single-factor analysis of the influence of the length of the space interval between intersections, the operating time of traffic light cycles, the number of cars in the queue, the road surface condition, and the category of the most inertial vehicles. The study involved a cluster analysis, which allowed identifying groups of lanes at intersections with similar traffic characteristics. The authors derived coefficients for the quantitative assessment of the influence of various factors on the recommended speed: the coefficient of queue passing dynamics (kd), which takes into account the road surface condition, and the coefficient of vehicle inertia in the queue (ki). The analysis showed that changes in the road surface conditions reduce the speed by 20-40%, an increase in the number of cars in the queue by more than five units reduces the speed by 15-30%, and the presence of vehicles of categories III (trucks from 3.5 to 12 tons) and IV (trucks over 12 tons) in the queue reduces the recommended speed by 10-25%. The multi-factor approach is based on the fuzzy logic method, which allows taking into account probabilistic fluctuations in the input parameters and their interrelationships. The obtained results can be used to optimize urban traffic, reduce the number of stops before intersections, increase the traffic capacity of signal-controlle. |
|---|---|
| ISSN: | 1451-2092 2406-128X |