The design of the wellbore trajectory directly affects the construction quality and efficiency of drilling. A good wellbore trajectory is conducive to guiding on-site construction, which can effectively reduce costs and increase productivity. Therefore, further optimization of the wellbore trajectory is inevitable and necessary. Based on this, aiming at the three-segment, five-segment, double-increase-profile extended reach wells, this paper considered the constraints of formation wellbore stability; formation strength; and the determination of the deviation angle, deviation point position, and target range by the work of deflecting tools. In addition, the optimization objective function of the shortest total length of the wellbore, minimum error of the second target, lowest cost, minimum friction of the lifting and lowering string, and minimum torque of rotary drilling were proposed and established. The objective function of the longest extension limit of the horizontal section of the extended reach well is established. Taking the 14-8 block of the Lufeng Oilfield in the eastern South China Sea as an example, the actual data of the field were modeled, and the independence of the objective function was verified by comparing the number of non-inferior solutions of the two objective functions. By normalizing simplified to double-, three-, and four-objective functions, using a genetic algorithm and particle swarm optimization results, it can be found that the new method of optimization design established in this paper has an obvious optimization effect compared with the original design.

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.