Lightweight Model for Pavement Defect Detection Based on Improved YOLOv7.

Existing pavement defect detection models face challenges in balancing detection accuracy and speed while being constrained by large parameter sizes, hindering deployment on edge terminal devices with limited computing resources. To address these issues, this paper proposes a lightweight pavement defect detection model based on an improved YOLOv7 architecture. The model introduces four key enhancements: first, the incorporation of the SPPCSPC_Group grouped space pyramid pooling module to reduce the parameter load and computational complexity; second, the utilization of the K-means clustering algorithm for generating anchors, accelerating model convergence; third, the integration of the Ghost Conv module, enhancing feature extraction while minimizing the parameters and calculations; fourth, introduction of the CBAM convolution module to enrich the semantic information in the last layer of the backbone network. The experimental results demonstrate that the improved model achieved an average accuracy of 91%, and the accuracy in detecting broken plates and repaired models increased by 9% and 8%, respectively, compared to the original model. Moreover, the improved model exhibited reductions of 14.4% and 29.3% in the calculations and parameters, respectively, and a 29.1% decrease in the model size, resulting in an impressive 80 FPS (frames per second). The enhanced YOLOv7 successfully balances parameter reduction and computation while maintaining high accuracy, making it a more suitable choice for pavement defect detection compared with other algorithms.

Characteristic Parameters of Magnetostrictive Guided Wave Testing for Fatigue Damage of Steel Strands.

Steel strands are widely used in structures such as bridge cables, and their integrity is critical to keeping these structures safe. A steel strand is under the working condition of an alternating load for a long time, and fatigue damage is unavoidable. It is necessary to find characteristic parameters for evaluating fatigue damage. In this study, nonlinear coefficients and attenuation coefficients were employed to evaluate fatigue damage based on magnetostrictive guided wave testing. Unlike pipe and steel wire structures, there is a phenomenon of a notch frequency when guided waves propagate in steel strands. The influence of the notch frequency on the nonlinear coefficient and attenuation coefficient is discussed. The relationship between the nonlinear coefficient, attenuation coefficient, and cyclic loading times was obtained through experiments. The amplitudes of the nonlinear coefficient and attenuation coefficient both increased with the increase in cyclic loading times. The experiments also showed the effectiveness of using these two characteristic parameters to evaluate fatigue damage.

Research on Micro/Nano Surface Flatness Evaluation Method Based on Improved Particle Swarm Optimization Algorithm.

Flatness error is an important factor for effective evaluation of surface quality. The existing flatness error evaluation methods mainly evaluate the flatness error of a small number of data points on the micro scale surface measured by CMM, which cannot complete the flatness error evaluation of three-dimensional point cloud data on the micro/nano surface. To meet the needs of nano scale micro/nano surface flatness error evaluation, a minimum zone method on the basis of improved particle swarm optimization (PSO) algorithm is proposed. This method combines the principle of minimum zone method and hierarchical clustering method, improves the standard PSO algorithm, and can evaluate the flatness error of nano scale micro/nano surface image data point cloud scanned by atomic force microscope. The influence of the area size of micro/nano surface topography data on the flatness error evaluation results is analyzed. The flatness evaluation results and measurement uncertainty of minimum region method, standard least squares method, and standard PSO algorithm on the basis of the improved PSO algorithm are compared. Experiments show that the algorithm can stably evaluate the flatness error of micro/nano surface topography point cloud data, and the evaluation result of flatness error is more reliable and accurate than standard least squares method and standard PSO algorithm.