Identifying lithofacies types from core drilling data presents significant challenges, especially given the limited number of physical drilling characteristics available for analysis. Traditional machine learning methods often face issues with poor training and testing due to these limitations. Addressing this, we propose a new method for processing core drilling data to improve the accuracy of deep artificial neural networks (DANNs) in lithofacies recognition. Our approach transforms torque, weight on bit (WOB), and rotational speed data into three square matrices, creating a novel three-channel lithofacies image. This method allows for the application of DANNs by converting the complex lithofacies recognition task into a more standard image recognition problem. The developed method dramatically increases the input vector dimensions, enhancing the richness of the data input. The validation of results revealed that the DANN model trained for merely 3000 iterations successfully predicted lithofacies types of all eight testing samples in a mere 2.85 ms, showcasing superior accuracy. The innovative drilling data processing method proposed in this study enables DANNs to identify lithofacies with increased speed and accuracy. This offers a new direction for other DANNs utilizing drilling data.
Pneumatic down-the-hole (DTH) hammer drilling technology has been used extensively in the fields of heat reservoir exploitation and geological exploration owing to its advantages of high efficiency and low pollution. However, the vibration near the bit is up to 40 g while DTH hammer drilling, which significantly affects the performance and longevity of the near-bit measurement while drilling (MWD). To enhance the environmental adaptability of the near-bit MWD in pneumatic DTH operations, a design method for a vibration-damping system based on the parameter optimization of a non-dominated sorting genetic algorithm II (NSGA-II) is proposed in this study. First, the whole structure of the near-bit MWD is designed, including the MWD sub-shell, sensors, measurement circuits, batteries, and connecting structures (the circuit unit). Secondly, this study analyzes the vibration characteristics of the pneumatic DTH hammer near the bit. According to the damping structure, the vibration response model for the circuit unit and the damping model are established. Thirdly, NSGA-II is employed to optimize the parameters of the damping model in terms of the low-frequency, high-intensity vibration characteristics near the bit in pneumatic DTH operations, thereby devising a damping scheme tailored to the unique conditions of DTH hammer drilling. Finally, vibration experiments were conducted to verify the effectiveness of the vibration-damping device. The experimental results indicate that within the vibration frequency range of 5–20 Hz and vibration level of 10–40 g, the peak attenuation rate of the circuit unit is more than 86.446%, and the improvement rate of the vibration stability of the system is more than 75.214%; the anti-vibration performance of the near-bit MWD system in DTH hammer drilling is improved remarkably. This study provides strong technical support for the stability of MWD equipment under such special working conditions. It has broad engineering application prospects.
The development of automation and intelligence in geological core drilling is not yet mature. The selection and improvement of drilling parameters rely mainly on experience, and adjustments are often made after drilling by evaluating the core, which introduces a lag and reduces the drilling efficiency. Therefore, this study first establishes a geological core drilling experiment platform to collect drilling data. Through the constructed geological core drilling experimental platform, the practical data at the drill bit can be directly obtained, solving the problem of the data from the surface equipment in the practical drilling differing from the practical data. Second, the back propagation (BP) algorithm is used to perform the ROP prediction, with weight on bit (WOB), torque (TOR), flow rate (Q), and rotation speed (RPM) as input parameters, and rate of penetration (ROP) as the output. Subsequently, correlation analysis is used to perform the feature parameter optimization, and the effects of bit wear and bit cutting depth on the experiment are considered. Finally, comparison with algorithms such as ridge regression, SVM and KNN shows that the ROP prediction model using the BP neural network has the highest prediction accuracy of 94.1%. The results provide a reference for ROP prediction and the automation of geological core drilling rigs.
The pipe-jacking inertial guidance method is a key technology to solve the guidance problems of complex pipe-jacking projects, such as long distances and curves. However, since its guidance information is obtained by gyroscope integration. System errors will accumulate over time and affect the guidance accuracy. To address the above issues, this study proposes an intelligent online system error correction scheme based on single-axis rotation and data backtracking. The method enhances system observability by actively exciting the sensor states and introducing data reuse technology. Then, a Bayesian optimization algorithm is incorporated to construct a multi-objective function. The algorithm autonomously searches for the optimal values of three key control parameters, thereby constructing an optimal correction strategy. The results show that the inclination accuracy improving by 99.36%. The tool face accuracy improving by 94.05%. The azimuth accuracy improving by 94.42% improvement. By comparing different correction schemes, the proposed method shows better performance in estimating gyro bias. In summary, the proposed method uses single-axis rotation and data backtracking, and can correct system errors in inertial navigation effectively. It has better value for engineering and provides a technical foundation for high-accuracy navigation in tunnel, pipe-jacking, and other complex tasks with low-cost inertial systems.