QLQiang Li

Qiang Li

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Qiang Li has a total of 6 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Deep Learning Model Ensemble Applied to Modulus Back-Calculation of Old Cement Concrete Rubblized Overlay Asphalt Pavement

    by Qiang Li, Pai Peng

    Accurately determining the modulus of each structural layer remains a key challenge in asphalt pavement design, construction quality control, and bearing capacity assessment. This study introduces an ensemble model combining a genetic algorithm-optimized backpropagation neural network (GA-BP) and a convolutional neural network (CNN) to back-calculate the dynamic modulus of asphalt pavement layers over rubblized old cement concrete structures. Using a dynamic deflection basin database created by our research team, we built a dataset of 1,552,000 pavement structure samples with Falling Weight Deflectometer (FWD) data. Based on this dataset, we developed regression models, including a backpropagation (BP) neural network, GA-BP, and CNN, to perform the back-calculation of dynamic modulus values. Performance testing revealed that the CNN model outperformed both the GA-BP and BP models in terms of accuracy and stability, as indicated by evaluation metrics (R2, MAE, RMSE, MAPE), with the following ranking: CNN > GA-BP > BP. Nonetheless, the maximum relative error across all three models remained notable. To address this, an ensemble model combining GA-BP and CNN was created, significantly enhancing the accuracy and stability of the back-calculation results. The proposed ensemble model was tested on-site with FWD data to estimate the dynamic modulus of asphalt pavement layers. The results demonstrated strong agreement with actual pavement performance and high consistency with numerical outcomes from three-dimensional (3D) dynamic finite element method simulations. These findings suggest that the GA-BP and CNN ensemble approach offers a reliable method for back-calculating the dynamic modulus of asphalt pavement layers over rubblized old cement concrete structures.


  • Simulating the mechanical response of asphalt pavement under falling weight dynamic loading

    by Qiang Li, Wentao Wang, Dongxu Liu

    To obtain a large number of dynamic mechanical responses of asphalt pavement structures under falling weight dynamic (FWD) loading in order to construct a deep learning training set, a method for transforming the dynamic–static mechanical responses of pavements based on a theoretical solution of the layered elastic system was constructed. Firstly, Abaqus was used to establish a three-dimensional mechanical analysis model of an asphalt pavement considering structural damping and to calculate the dynamic mechanical response of a typical pavement structure. Then, the main factors affecting the dynamic mechanical response of pavement surfaces structures were thoroughly analysed and a multi-variate regression analysis method was used to establish a transformation model for the dynamic and static mechanical responses of a three-layer basic pavement structure system. Finally, using a structural conversion method, the conversion model was extended to a multi-layer asphalt pavement structure to complete the calculation of the dynamic mechanical response. The measured dynamic mechanical response under FWD loading was found to be very consistent with the calculation results based on the proposed method, meaning that the model is reliable and accurate.


  • Open Access

    Reflection Crack Analysis of Asphalt Overlay on Cement Concrete Pavement Based on XFEM

    by Qiang Li, Zhixiang Chen, Shaohui Luo

    Based on the improved Paris formula, the reflection cracking characteristics of asphalt overlay on the cement concrete pavement are carefully scrutinized. The fatigue life is also predicted through the indoor simulation tests and establishing the two‐ and three‐dimensional extended finite‐element method (XFEM) models. Four fracture factors of the Paris formula in the asphalt mixture are appropriately calculated by fitting the N‐a curve of the indoor test, and their predicted values are then exploited in the numerical simulations. The obtained results show that the numerical model can successfully predict the results of the indoor simulation test. It indicates that the XFEM has apparent advantages in examining the reflection cracking of the asphalt overlay on the cement concrete pavement.