The Permian igneous rock in Shunbei Oilfield exhibits high rock strength, which results in a low rate of penetration (ROP) and shortens the cutter’s service life. It is necessary to analyze and evaluate the rock breaking effect of cutters. However, at this stage, the evaluation of the rock breaking effect has been limited to comparing the sizes of the mechanical specific energy (MSE), and the change in the rock breaking efficiency caused by the difference in the shape of the cutters’ surface has not been considered. Therefore, through the establishment of numerical simulation models of a circular cutter, bevel cutter, axe cutter, wedge cutter, and triangular cutter, the evaluation of the rock breaking efficiency of special-shaped cutters was completed. The results show that the triangular cutter and the wedge cutter are suitable for the front row cutter of the polycrystalline diamond compact bit (PDC); the triangular cutter is suitable for drilling into medium–hard formations, the wedge cutter is suitable for drilling into hard formations, and the bevel cutter is suitable for the back row cutter of the PDC, to assist other cutters in the process of rock breaking. The research results can provide the basis for the selection of PDC bit cutters and the design optimization of the bit.

The accurate prediction and monitoring of rock drillability are essential for geomechanical modeling and optimizing drilling parameters. Traditional methods often rely on laboratory core experiments and well logging data to evaluate rock drillability. However, these methods can only obtain core samples and sonic logging data in drilled wells. To enable the real-time monitoring of bottom-hole rock drillability during drilling, we propose the following novel approach: data fusion and a CNN-GBDT framework for surface-based real-time monitoring. The specific process involves using 1D-CNN convolution to extract deep features from historical wells’ drilling data and sonic log data. These deep features are then fused with the original features and passed to the GBDT framework’s machine learning model for training. To validate the effectiveness of this method, this study conducted a case analysis on two wells in the Missan Oil Fields. CNN-GBDT models based on XGBoost, LightGBM, and CatBoost were established and compared with physical methods. The results indicate that the CNN-GBDT model centered on LightGBM achieved a mean square error (MSE) of 0.026, which was one-tenth of the MSE of 0.282 of the physical evaluation method. Furthermore, the effectiveness of the proposed CNN-GBDT framework for monitoring rock drillability suggests potential applications in monitoring other bottom-hole parameters.