The new method of rock breaking based on the combination of circular sawblade and conical pick was proposed to improve the effectiveness of hard rock breaking. The numerical simulation method was applied to research the conical pick cutting arc rock plate by ANSYS/LS‐DYNA. The conical pick cutting arc rock plate numerical simulation model was established to research the influence of arc rock plate structural parameters and cutting parameters on cracks formation and propagation of the arc rock plate and the cutting force in the process of conical pick cutting arc rock plate. The amount of cracks is positively correlated with arc rock plate thickness, the cutting speed, and distance of cutting point to arc rock plate central axis and negatively correlated with the cutting angle. The mean peak cutting force is positively correlated with the thickness of arc rock plate and the distance of cutting point to arc rock plate central axis; however, it is negatively correlated with the arc rock plate height and width and cutting angle of conical pick. The simulation results can be used to predict the conical pick work performance with various cutting parameters and structural parameters.

The conical pick is the most crucial tool of roadheader for breaking rock, establishing the conical pick cutting rock and conical pick fatigue life numerical simulation models to investigate the influence of cutting parameters on rock damage, average peak cutting force, specific cutting energy and the conical pick fatigue life. The research results indicate that the width and depth of rock damage increase with increasing cutting depth and cutting speed. The average peak cutting force and the specific cutting energy have the same changing tendency. The changing trend of conical pick fatigue life and conical pick stress is opposite relationship. The optimum cutting angle of the conical pick cutting rock is 45°. Applying the research results for guiding the optimization of the cutting parameters reduces the specific cutting energy and stress and improves the conical pick fatigue life.

Compaction Measurement Value (CMV) is the most widely used quality evaluation index for intelligent compaction. However, with the growth of compaction degree, CMV becomes less accurate due to increased reaction force from densified geomaterials. To solve this problem, this paper proposes a more accurate intelligent compaction quality evaluation index, acceleration intelligent compaction value (AICV). Based on field measurement data analysis, AICV turned out to be effective to elevate quality evaluation accuracy. Additionally, the singularities were detected by $3\sigma$ normal distribution in order to assess the uniformity of subgrade compaction quality. Based on the semivariogram analysis method of spatial statistics, CMV and AICV were analyzed for spatial correlation, and the influence range of intelligent compaction technology employed for subgrade was evaluated. The results from this study provide a basis for further research on precision control and uniformity analysis of intelligent compaction technology.

To improve the accuracy of computer vision-based bridge crack-width identification, two factors were investigated in this study. First, a fully convolutional neural network combined with a U-Net architecture was used to extract crack pixels and a crack midline (i.e., crack skeleton). A database including 100 images with 572 × 572 pixels labelled for cracks was developed. The results revealed a mean of 84.4% of the average mean intersection over union of the U-Net. In addition, a crack-width direction identification method based on the slope of the crack skeleton was proposed, and the accurate extraction of the nonuniform width parameter along the crack was realised. Second, to obtain a mapping from the width pixels to width physical dimensions, a pixel calibration experiment was conducted. Finally, a nonlinear regression model of the distance, focal length, and actual pixel size was developed to overcome the light distortion of the camera. Ultimately, the combination of the two factors completed a high-precision extraction of the entire process of crack-width identification and achieved a 0.01-mm precision under a 96% guarantee rate.

Conical picks are applied to rock breaking, and the cutting parameters greatly influence cutting performance and rock damage. A conical pick rock-cutting numerical simulation model and software to provide a quantitative analysis of rock damage are established to research the influence of cutting parameters on cutting force and rock damage. The research results indicated that the average peak cutting force decreases with an increased cutting angle, and the average peak cutting force increases with a decreased cutting speed. The average peak cutting force of the second conical pick increases as the distance between double conical picks increases in the process of rock-cutting with double conical picks. There is a positive correlation between the volume of rock damage, the volume of rock breaking, and the cutting force of the conical pick. The research results provide a reference for optimizing the cutting parameters of conical picks.

In the rock cutting process, conical pick wear is often encountered. In order to restrain this condition, a saw blades and conical pick combined cutting method was put forward. Saw blades were employed to slit the rock for increasing the free surface, and then the conical pick was used to break the rock. To research the cutting performance of the new cutting method, the corresponding experimental device and a three‐dimensional finite element model are established. In order to obtain crack propagation and fragment separation and to study the fracture process of the rock plate, a damage constative model and failure mechanism were combined in the numerical model. The mechanical tests were carried out to achieve the mechanical parameters of the rock. To investigate different parameters affecting rock plate cutting performance, experiments with different compressive strengths, physical parameters, and cutting depths were carried out. Moreover, the confining pressures affecting the cutting performance were adopted to simulate deep mining conditions. The experimental results demonstrated that the peak cutting force shows the exponential positive correlation with compressive strength, thickness of the rock plate, and cutting depth of the conical pick, and exhibits the exponential positive correlation with rock plate height and width. Besides, the numerical simulation results show that peak cutting force and confining pressure have a binomial relationship.