Upgradation of pavement deterioration models for urban roads by non-hierarchical clustering
- PDF / 505,788 Bytes
- 9 Pages / 595.32 x 841.92 pts (A4) Page_size
- 19 Downloads / 204 Views
International Journal of Pavement Research and Technology Journal homepage: www.springer.com/42947
Upgradation of pavement deterioration models for urban roads by non-hierarchical clustering Rejani V. U.*, Sunitha Velayudhan, Samson Mathew Department of Civil Engineering, NIT Tiruchirappalli, Tamil Nadu 620015, India Received 13 April 2020; received in revised form 4 August 2020; accepted 4 August 2020
Abstract
Pavements, being a significant component of urban infrastructure, their maintenance and rehabilitation to the desired service ability level is a challenging problem faced by engineers. The development of a reliable pavement deterioration model is essential to devise proper maintenance policies. This exploratory paper presents the development of network-level pavement performance prediction models for the selected arterial and sub-arterial roads of Tiruchirappalli city, India. Road inventory, traffic volume, maintenance history, pavement condition, and roughness data of the study area are collected periodically for seven years. The Pavement Condition Index (PCI) is determined from the data collected through visual evaluation of the type, severity, and amount of pavement distress. Roughometer is deployed to obtain the International Roughness Index. The parameters which influence paveme nt deterioration vary widely for different roads within the same network. The pavement sections are assembled into three homogene ous clusters using k-means clustering, which is a nonhierarchical clustering algorithm, so that they can be modeled with better acceptability. Pavement performance predic tion models are generated for different clusters using multiple linear regression analysis, and comparison is made with that developed for non-clustered data. The error in prediction is found to be less for clustered models. While the pavement sections in cluster 2, when left unmaintained, deteriorates from a PCI value of 100 to 77 in 5 years, those belonging to cluster 3 are found to deteriorate from 100 to 13. The variation in the deterioration process and the significance of clustering pavement sections for efficient pavement maintenance management is established. Keywords: Urban pavements; Pavement maintenance; Pavement condition index; Pavement deterioration models; Clustering
1. Introduction The up keeping of road infrastructure requires methodical tactics involving condition evaluation, performance prediction, program optimization, and development of maintenance strategies. In the 1960s, the idea of Pavement Management Systems (PMS) was used for the first time to design the methodical approach to pavement design and management [1]. Developments in associated technologies took place in the 1970s, and the acquired knowledge was recorded in the book “Pavement Management Systems” [2]. Implementing properly designed PMS depends on factors like credible data, rational models for performance prediction, and user-friendly software for data management. Data pertaining to pavement condition is a vital element of PMS. The data gather
Data Loading...
