Pavement maintenance and rehabilitation optimization based on cloud decision tree

The pavement management system (PMS) consists of several components including data collection, analysis, and reporting procedures. This system helps make decisions about the prioritization of road sections and selecting optimal maintenance strategy for the related road pavement networks. Considering the deteriorating rate of pavement sections and the limited budget and resources, it is important to find the most optimal maintenance and rehabilitation (M&R) scenarios for each pavement section. This study presents a model based on the cloud decision tree (CDT) theory for selecting the most optimal M&R strategies. A CDT system is presented for Iran’s national road network. The system includes a general decision-making model and various decision trees for every province of the country. Exclusive decision-making models were presented for freeways, highways, and main roads. Furthermore, different decision tree models are presented based on roads Annual Average Daily Traffic (AADT). Using the presented theory resulted in a general model with an accuracy of 80%. Evaluation of acquired decision trees showed that fatigue cracking and International Roughness Index (IRI) are the mo st important parameters to determine the appropriate M&R scenarios. Using these parameters provided results close to the re suits of experts’ surveys under real conditions, regardless of rank and traffic volume of the road sections.

[1]  Samer Madanat,et al.  Simultaneous Network Optimization Approach for Pavement Management Systems , 2014 .

[2]  Markus Hofmann,et al.  RapidMiner: Data Mining Use Cases and Business Analytics Applications , 2013 .

[3]  Sulin Pang,et al.  C5.0 Classification Algorithm and Application on Individual Credit Evaluation of Banks , 2009 .

[4]  Halil Ceylan,et al.  Integrated fuzzy analytic hierarchy process and VIKOR method in the prioritization of pavement maintenance activities , 2016 .

[5]  Serdal Terzi,et al.  Modeling the Pavement Present Serviceability Index of Flexible Highway Pavements Using Data Mining , 2006 .

[6]  Adelino Ferreira,et al.  A Multi-Objective Optimization-Based Pavement Management Decision-Support System for Enhancing Pavement Sustainability , 2016 .

[7]  Emad Elbeltagi,et al.  Optimum analysis of pavement maintenance using multi-objective genetic algorithms , 2015 .

[8]  Shelley M Stoffels,et al.  Network-Level Pavement Roughness Prediction Model for Rehabilitation Recommendations , 2010 .

[9]  Le Zhang,et al.  General Iterative Approach for System-Level Joint Optimization of Pavement Maintenance, Rehabilitation, and Reconstruction Planning , 2017 .

[10]  Mbakisya Onyango,et al.  Analysis of cost effective pavement treatment and budget optimization for arterial roads in the city of Chattanooga , 2018 .

[11]  Guoqing Zhou,et al.  Integration of GIS and Data Mining Technology to Enhance the Pavement Management Decision Making , 2010 .

[12]  Víctor Yepes,et al.  Optimal pavement maintenance programs based on a hybrid Greedy Randomized Adaptive Search Procedure Algorithm , 2016 .

[13]  W R Hudson,et al.  PAVEMENT MANAGEMENT SYSTEMS LEAD THE WAY FOR INFRASTRUCTURE MANAGEMENT SYSTEMS , 1994 .

[14]  Xingyu Gu,et al.  Multi-objective optimization for asphalt pavement maintenance plans at project level: Integrating performance, cost and environment , 2015 .

[15]  Jinwoo Lee,et al.  Jointly optimal policies for pavement maintenance, resurfacing and reconstruction , 2015, EURO J. Transp. Logist..

[16]  Sigit Pranowo Hadiwardoyo,et al.  Pavement Maintenance Optimization Strategies for National Road Network in Indonesia Applying Genetic Algorithm , 2017 .

[17]  Nilima P. Patil,et al.  Comparison of C5.0 & CART Classification algorithms using pruning technique , 2012 .