Oral Presentation Ninth International Symposium on Life-Cycle Civil Engineering 2025

Multi-objective maintenance optimization of asphalt pavement systems: A risk and sustainability approach (108238)

Jiyu Xin 1 , Lianzhen Zhang 1 , Dan M. Frangopol 2 , Mitsuyoshi Akiyama 3
  1. Harbin Institute of Technology, Harbin, China
  2. Lehigh University, Bethlehem, PA, USA
  3. Waseda University, Tokyo, Japan

Asphalt pavements are essential components of roadway networks in any nation, facilitating the mobility of freight and commodities for economic vitality and providing access to a range of users as societal benefits. The management of existing pavement assets is becoming increasingly important as highway infrastructure ages worldwide. Subject to numerous stressors, including increasing traffic loads, diverse climatic conditions, and the aging of asphalt materials, asphalt pavements can begin to deteriorate from the moment they enter service. If not managed in a timely and effective manner, this deterioration can lead to a significant decline or even failure in structural functionality and safety. To achieve optimal pavement management, sustainability considerations throughout the entire pavement life-cycle must be incorporated into the decision-making process under uncertainty. This study presents a novel sustainability-informed management optimization for asphalt pavement. First, a deep neural network (DNN) model is trained using the Long-Term Pavement Performance (LTPP) database to learn the nonlinear and complex relationships among multiple performance indicators of asphalt pavement (i.e., the international roughness index (IRI), rut depth, and alligator and transverse cracking) and their associated parameters (i.e., climate, traffic, and pavement structure and properties). Based on the multiple time-dependent limit-state functions that incorporate the uncertainties associated with these parameters, the DNN model prediction, and the IRI measurement, a Monte Carlo simulation is conducted to estimate the system failure probability of asphalt pavement. Finally, a genetic algorithm-based tri-objective optimization is utilized to identify the optimal maintenance and rehabilitation actions that minimize detrimental economic, environmental, and social consequences throughout the pavement’s life-cycle. The capabilities of the proposed approach are illustrated using LTPP asphalt pavement sections in Pennsylvania and Florida, USA. Future studies should continue with the aim of achieving asphalt pavements that ultimately produce positive outcomes, such as generating more energy than they consume.