Inappropriate maintenance and rehabilitation strategies cause many problems such as maintenance budget waste, ineffective pavement distress treatments, and so forth. A method based on a machine learning algorithm called deep reinforcement learning (DRL) was developed in this presented research in order to learn better maintenance strategies that maximize the long‐term cost‐effectiveness in maintenance decision‐making through trial and error. In this method, each single‐lane pavement segment can have different treatments, and the long‐term maintenance cost‐effectiveness of the entire section is treated as the optimization goal. In the DRL algorithm, states are embodied by 42 parameters involving the pavement structures and materials, traffic loads, maintenance records, pavement conditions, and so forth. Specific treatments as well as do‐nothing are the actions. The reward is defined as the increased or decreased cost‐effectiveness after taking corresponding actions. Two expressways, the Ningchang and Zhenli expressways, were selected for a case study. The results show that the DRL model is capable of learning a better strategy to improve the long‐term maintenance cost‐effectiveness. By implementing the optimized maintenance strategies produced by the developed model, the pavement conditions can be controlled in an acceptable range.

High porosity with interconnected voids between aggregate particles is the primary characteristic of portland cement pervious concrete (PCPC), which, however, causes a significant decrease in its strength and abrasion resistance. In this study, latex and fiber were added to improve the abrasion resistance of PCPC mixtures. Laboratory tests were conducted to evaluate the performance of latex-modified pervious concrete with a particular focus on abrasion resistance. Test results show that adding latex desirably improved strength and abrasion resistance of PCPC, whereas fiber did not show a significant effect on the mechanical properties of PCPC. In addition, the asphalt pavement analyzer (APA) abrasion test was found to be feasible for evaluating the abrasion resistance of pervious concrete.

Moisture-induced damage has long been recognized as one of the major concerns for asphalt pavements. To mitigate potential moisture damage, one general method is to add mineral antistripping additives or liquid antistripping agents into hot-mix asphalt (HMA) mixtures. In this study, a comparative laboratory experiment was conducted to investigate the effectiveness of cementitious fillers on moisture susceptibility of HMA mixtures. Five types of cementitious fillers were considered: fly ash, cement kiln dust, and three types of hydrated lime with different finenesses. The laboratory performance of HMA mixtures subjected to moisture conditioning was evaluated through the following tests: dynamic modulus test; superpave indirect tensile tests; and tensile strength ratio test. The test results indicate that the cementitious fillers were generally effective in reducing the moisture susceptibility of HMA mixtures. The finer the hydrated lime particle, the more resistant the asphalt mixtures. In addition, dynami...