The accurate and frequent measurement of the drilling fluid’s rheological properties is essential for proper hydraulic management. It is also important for intelligent drilling, providing drilling fluid data to establish the optimization model of the rate of penetration. Appropriate drilling fluid properties can improve drilling efficiency and prevent accidents. However, the drilling fluid properties are mainly measured in the laboratory. This hinders the real-time optimization of drilling fluid performance and the decision-making process. If the drilling fluid’s properties cannot be detected and the decision-making process does not respond in time, the rate of penetration will slow, potentially causing accidents and serious economic losses. Therefore, it is important to measure the drilling fluid’s properties for drilling engineering in real time. This paper summarizes the real-time measurement methods for rheological properties. The main methods include the following four types: an online rotational Couette viscometer, pipe viscometer, mathematical and physical model or artificial intelligence model based on a Marsh funnel, and acoustic technology. This paper elaborates on the principle, advantages, limitations, and usage of each method. It prospects the real-time measurement of drilling fluid rheological properties and promotes the development of the real-time measurement of drilling rheological properties.

In gas drilling operations, the rate of penetration (ROP) parameter has an important influence on drilling costs. Prediction of ROP can optimize the drilling operational parameters and reduce its overall cost. To predict ROP with satisfactory precision, a stacked generalization ensemble model is developed in this paper. Drilling data were collected from a shale gas survey well in Xinjiang, northwestern China. First, Pearson correlation analysis is used for feature selection. Then, a Savitzky-Golay smoothing filter is used to reduce noise in the dataset. In the next stage, we propose a stacked generalization ensemble model that combines six machine learning models: support vector regression (SVR), extremely randomized trees (ET), random forest (RF), gradient boosting machine (GB), light gradient boosting machine (LightGBM) and extreme gradient boosting (XGB). The stacked model generates meta-data from the five models (SVR, ET, RF, GB, LightGBM) to compute ROP predictions using an XGB model. Then, the leave-one-out method is used to verify modeling performance. The performance of the stacked model is better than each single model, with R² = 0.9568 and root mean square error = 0.4853 m/h achieved on the testing dataset. Hence, the proposed approach will be useful in optimizing gas drilling. Finally, the particle swarm optimization (PSO) algorithm is used to optimize the relevant ROP parameters.

Rock-socketed piles are commonly used in pile foundations for large buildings because of their excellent load-bearing characteristics. The roughness of the pile–rock interface affects the load transfer and the ultimate side resistance of the pile. In this work, a laser radar system is developed to measure the surface roughness of a dry bored pile and the shape of the borehole, and a three-dimensional model of the borehole is reconstructed based on the laser point cloud. The 3D surface model was used to extract the vertical contour lines in different directions and thus calculate the roughness of the pile. A numerical simulation of the real measured 3D model using FLAC3D is presented. A borehole of a real rock-socketed pile was measured and simulated. The results show that, although the working load is carried by both the side and base resistances, the former plays a major role. The slow-varying load-settlement curve indicates that the pile has a superior load–bearing capacity, and the maximum allowable settlement should be considered in the application. The simulations, using the actual piles tested, produced a more realistic load response and were able to predict the load-bearing performance of the piles more accurately. Furthermore, this approach offers a reference for the design of rock-socketed piles.

Accurate wellbore trajectory prediction is of great significance for enhancing the efficiency and safety of directional drilling in coal mines. However, traditional mechanical analysis methods have high computational complexity, and the existing data-driven models cannot fully integrate non-sequential features such as stratum lithology. To solve these problems, this study proposes a parallel input gated recurrent unit (Pi-GRU) model based on the TensorFlow framework. The GRU network captures the temporal dependencies of sequence data (such as dip angle and azimuth angle), while the BP neural network extracts deep correlations from non-sequence features (such as stratum lithology), thereby achieving multi-source data fusion modeling. Orthogonal experimental design was adopted to optimize the model hyperparameters, and the ablation experiment confirmed the necessity of the parallel architecture. The experimental results obtained based on the data of a certain coal mine in Shanxi Province show that the mean square errors (MSE) of the azimuth and dip angle angles of the Pi-GRU model are 0.06° and 0.01°, respectively. Compared with the emerging CNN-BiLSTM model, they are reduced by 66.67% and 76.92%, respectively. To evaluate the generalization performance of the model, we conducted cross-scenario validation on the dataset of the Dehong Coal Mine. The results showed that even under unknown geological conditions, the Pi-GRU model could still maintain high-precision predictions. The Pi-GRU model not only outperforms existing methods in terms of prediction accuracy, with an inference delay of only 0.21 milliseconds, but also requires much less computing power for training and inference than the maximum computing power of the Jetson TX2 hardware. This proves that the model has good practicability and deployability in the engineering field. It provides a new idea for real-time wellbore trajectory correction in intelligent drilling systems and shows strong application potential in engineering applications.

In recent years, small-borehole wireline coring has become increasingly dependent on trajectory control, downhole condition sensing, and real-time directional decision-making. However, under low-flow conditions, conventional MWD pulser heads tend to generate relatively small pulse amplitudes; as hole depth increases, the pressure signal undergoes stronger attenuation and becomes more susceptible to noise interference, making it difficult to sustain a decodable amplitude under a limited pump-pressure budget. Existing studies have mainly focused on surface decoding and signal processing and therefore do not improve, at the source-structure level, the amplitude output and tool-section incremental pressure loss in low-flow operation. Accordingly, this study develops a compact small-diameter mud-pulse pulser head for 1–3 L/s operation and evaluates its performance through an integrated workflow combining theoretical screening, numerical simulation, and shallow-hole field testing focused on hydraulic pulse generation and surface detectability. The results show that, after selecting appropriate bypass-orifice sets, the proposed pulser head produces stable pressure pulses meeting the surface decoding threshold across 1–3 L/s, while maintaining the tool-section incremental pressure loss within 0.5 MPa over the main operating range. The findings further indicate that, in low-flow regimes, the achievable decoding margin and the incremental-loss ceiling are primarily governed by the upstream hydraulic architecture. This work provides a practical basis for reliable low-flow mud-pulse telemetry in small-borehole wireline coring.

Trenchless horizontal directional drilling is the most widely used method in trenchless pipe-laying in China, of which the main formation is Quaternary strata. How to ensure the stability of the hole wall is the key issue to the success of the project in the drilling process. In this paper, a drilling fluid of powerful inhibition based on polyvinyl alcohol (PVA) was researched for trenchless horizontal directional drilling. This type of drilling fluid has a film-forming property, which can form a membrane-like substance if left to stand in air, and have a good effect on the stability of the hole wall in Quaternary strata. The author's research shows that: the polyvinyl alcohol (PVA) based drilling fluid of powerful inhibition has a better rheology and a stronger compatibility with other drilling fluid material, after investigating and analyzing a series of experiments for this kind of drilling fluids. It can meet the cleaning requirements of long horizontal directional bore hole if used with PAC. Compatibility with SPNH (brown coal resin) can reduce the loss of filtration and get a greater effect on lubrication drag reduction. The film-forming property and wall-protecting effect is particularly obvious when PVA is applied at the amount of 1.5% ~ 3%, especially suitable for trenchless horizontal directional drilling.