Piezoelectric energy harvesting in pavement is an advanced energy saving technology. It is carried out by laying the piezoelectric material in the pavement structure and converting the mechanical energy into electrical energy. The current energy harvester has difficulty meeting the complex requirements of pavements. In order to develop the pavement piezoelectric energy harvesting technology, in this paper, a stacked mode for a piezoelectric energy harvester is designed. The computer-controlled pressure testing machine (WHY-2000, Shanghai Hualong Test Instruments Corporation, Shanghai, China) was used to test the compressive property and the one–third-scaled accelerated instrument Model Mobile Load Simulator (MMLS-1/3) was used to test the fatigue properties of the piezoelectric transducer. Results showed that the designed piezoelectric transducer could bear loadings up to 150 kN, which can meet road traffic loading requirements. The piezoelectric properties of the transducer remain good after 100,000 cyclic loadings. The indoor laboratory test and the on-site test show that the piezoelectric transducer can work in real pavement in actual traffic conditions. The open circuit voltage can reach 280 V, which can provide enough electricity for sensing systems in the pavements. In all, the proposed new piezoelectric transducer provides a promising future for green energy use in the pavement industry.

Fundamental understanding of micro-mechanical behaviors in bitumen, including phase separation, micro-friction, micro-abrasion, etc., can help the pavement engineers better understand the bitumen mechanical performances at macroscale. Recent researches show that the microstructure evolution in bitumen will directly affect its surface structure and micro-mechanical performance. In this study, the bitumen microstructure and micro-mechanical behaviors are studied using Atomic Force Microscopy (AFM) experiments, Phase Dynamics Theory and Molecular Dynamics (MD) Simulation. The AFM experiment results show that different phase-structure will occur at the surface of the bitumen samples under certain thermodynamic conditions at microscale. The phenomenon can be explained using the phase dynamics theory, where the effects of stability parameter and temperature on bitumen microstructure and micro-mechanical behavior are studied combined with MD Simulation. Simulation results show that the saturates phase, in contrast to the naphthene aromatics phase, plays a major role in bitumen micro-mechanical behavior. A high stress zone occurs at the interface between the saturates phase and the naphthene aromatics phase, which may form discontinuities that further affect the bitumen frictional performance.

Crack is one of the important pavement damages. The number and types of cracks are usually collected and inspected by human, but lately computer vision has shown great potential for automatically identifying pavement cracks. However, training a convolutional neural network (CNN) requires large amount of data. The limited number of crack images and the variety of crack image background put challenges for developing CNN model with high accuracy. This study proposes an intelligent method for crack pattern classification based on limited field images. The proposed method has a two-step data preprocessing. It first applied data augmentation method to enlarge the dataset, solving the data imbalance problem and providing more training data. Then a crack extraction method was applied to convert the original image into a binary back-and-white image. This step significantly reduced the input feature and simplified the model. Both of data preprocessing steps were designed to decrease the bias of the model. Then we performed a model selection and hyper-parameter tunning for CNN. We explored the application of AlexNet, SE-Net, and ResNet with a variety of configurations. The results show that the proposed data augmentation can enlarge the dataset significantly. The crack extraction also significantly increased the test accuracy. The ResNet with 50 layers has the highest test accuracy. With data augmentation, crack extraction and model selection combining together, the final approach can improve the test accuracy from 52.68% to 87.50% compared to the original limited images. The result suggests our proposed method works well to classify crack images of asphalt pavement with limited sample size.

Efficient and accurate road distress detection is crucial for infrastructure maintenance and transportation safety. Traditional manual inspections are labor-intensive and time-consuming, while increasingly popular automated systems often rely on computationally intensive devices, limiting widespread adoption. To address these challenges, this study introduces MobiLiteNet, a lightweight deep learning approach designed for mobile deployment on smartphones and mixed reality systems. Utilizing a diverse dataset collected from Europe and Asia, MobiLiteNet incorporates Efficient Channel Attention to boost model performance, followed by structural refinement, sparse knowledge distillation, structured pruning, and quantization to significantly increase the computational efficiency while preserving high detection accuracy. To validate its effectiveness, MobiLiteNet improves the existing MobileNet model. Test results show that the improved MobileNet outperforms baseline models on mobile devices. With significantly reduced computational costs, this approach enables real-time, scalable, and accurate road distress detection, contributing to more efficient road infrastructure management and intelligent transportation systems.

As one of the most important properties of road, the adaption to roads with different macro-textures may significantly affect the autonomous driving technologies since road texture directly affects the skidding resistance and tire noise. Therefore, it is of great significance to detect and analyze the road macro texture with respect to different pavement types and service conditions. Generally, transportation engineers may face problems such as small dataset size, unbalanced dataset, etc. To solve these problems, this study aims to recognize the pavement texture using the deep learning approaches. The pavement texture data was first visualized using image processing methods, and then augmented using the traditional methods as well as a deep learning approach, i.e. Generative Adversarial Network (GAN) model. The Random Forest (RF) algorithm and the DenseNet network were both employed, where the overall classification accuracy of the original dataset was 50% and 59%, respectively, and the accuracy of the data augmented by the traditional methods was 58% and 70%, respectively. Test results show that, after 250,000 generations of training, GAN model was able to generate new pavement texture images with high quality, and the classification accuracy on the test dataset using DenseNet improved to 82%. It was discovered that the deep learning methods had a better performance for pavement texture recognition than manual classification and traditional machine learning methods. Furthermore, it was also found that adding noise in the original datasets as an augmentation method had a negative impact on the classification accuracy.

A wide range of literature on predominant green technologies for sustainable pavements is summarized in this paper. It covers two major aspects: energy harvesting technologies and permeable pavement systems. Fundamental mechanics of energy harvesting techniques and possible designs of energy harvesters are described, with the evaluation of energy conversion efficiency, and advantages and disadvantages. In addition, the designs of permeable pavement systems are discussed, along with their advantages and disadvantages. The latest technical innovations are highlighted. It is found that green technologies are promising for developing more sustainable pavements. Application issues are also pointed out, including construction challenges, durability, and life‐cycle cost‐benefit assessment. Future research directions are suggested to address practical challenges, such as efficient design, construction challenge, timely maintenance, and life‐cycle performance assessment.