Significant thermal dynamics occur during both well construction and injection-production cycles in underground energy storage systems. Accurately determining the wellbore temperature distribution is crucial for optimizing drilling processes, enhancing energy storage efficiency, and evaluating reservoir thermal impacts. Existing measurement-while-drilling (MWD) temperature technologies are mostly limited to single-point measurements at the bottomhole, making it difficult to obtain a full wellbore temperature profile. This study proposes a novel microchip logging technology that achieves breakthroughs in power control and high-temperature resistance through optimized system architecture and workflow, with a maximum operating temperature of 160 °C and the ability to function continuously for 5 h under high-temperature conditions. Field tests successfully captured dynamic temperature data during the microchips’ circulation with the drilling fluid. The study established a temperature field model, applied the temperature measurement data to the model improvement, and analyzed the temperature evolution laws throughout the entire process, including bottomhole circulation, reaming operations, and microchip deployment. The model exhibits excellent consistency with the measured values, which is significantly higher than that of traditional models. The research indicates that this technology can be extended to temperature monitoring during cyclic injection and production processes in underground energy storage systems, supporting the design and operation of underground renewable energy storage (URES) systems.

Drilling operations depend not only on controlling surface parameters but also on keeping bottom-hole assembly (BHA) components structurally sound. The BHA is the lower portion of the drill string in a drilling operation – the part that actually contacts the wellbore and guides the drilling process. Failures, especially at the connection between the flow diverter and the drive shaft behind the mud-motor power section, can cause major non-productive time (NPT), high costs, and poor performance. These failures are often linked to combined surface and downhole rotational speeds and high bending moments, which are common during directional drilling. To reduce this risk, we present a new method for real-time health monitoring and remaining useful life (RUL) estimation of these connections. The method combines physics-based fatigue modeling with machine-learning estimators, making it possible to track connector use across time and jobs using serialized component data. The system processes real-time drilling parameters to estimate downhole rotational speed (RPM) and bending moment. When measurement-while-drilling (MWD) data are available, direct RPM values are used; otherwise, a predictive model based on temperature, flow rate, and differential pressure is applied. Bending moment is inferred from drilling parameters and BHA design. The framework then calculates fatigue damage with connector-specific S–N (stress–number of cycles) curves and updates both current and cumulative RUL values. This helps operators make proactive decisions and lowers the risk of expensive failures. Tests with historical drilling data show strong agreement between predicted damage and observed connector failures, proving that the approach works in the field. The solution is already integrated into a commercial platform and used by field teams. Case studies show it reduces unexpected failures, cuts non-productive time, and improves the efficiency of directional drilling.

Discontinuous structures in coal mine roadway roofs, such as rock interfaces and joint fractures, are critical factors leading to surrounding rock instability. The use of Measurement While Drilling (MWD) technology to identify geological formations has become a growing trend. However, there is still a lack of rock structure recognition methods that offer high accuracy, efficiency, and strong generalizability. Therefore, this study acquired four drilling parameters including thrust, torque, modulation specific energy (SEM), and rock drillability assessment (RDA) through drilling experiments. By leveraging the Bayes algorithm, which has high precision, efficiency, and low cost, a change point detection model for drilling parameters was established, and a multi-parameter fusion criterion was proposed for identifying rock structures. The results show that for single rock interface identification, the errors of thrust, torque, SEM, and RDA were 13.3 mm, 4.6 mm, 4.4 mm, and 18.3 mm, respectively. For multiple rock interface identification, the recognition rates were 83.3%, 100.0%, 66.7%, and 83.3%, respectively. Moreover, the absolute value of the magnitude index (SLP) at the interface location was generally the highest among all change points. In multi-change-point detection, the SLP threshold should be set at ± 0.2. It is worth noting that the SLP value is correlated with data fluctuation intensity; greater fluctuation leads to higher SLP values at change points. This study contributes significantly to enabling intelligent perception of rock structures and improving the quality of rock mass control.

ABSTRACT Investigative drilling (ID) is an innovative measurement while drilling (MWD) technique implemented in various site investigation projects across Australia. While the automated drilling feature of ID substantially reduces noise in drilling data streams, data cleaning remains essential to remove anomalies for accurate strata classification and prediction of soil and rock properties. This study employed three machine learning algorithms – IsoForest, one-class SVM and DBSCAN – to automate the data cleaning process for ID rock drilling data. Two contexts were examined: (1) removing anomalies in rock drilling data, and (2) removing both anomalies and soil data in mixed rock drilling data. The analysis revealed that all three algorithms outperformed traditional statistical methods (the 3σ rule and IQR method) in both tasks, achieving a good balance between true and false positive rates, though hyperparameter tuning was required for one-class SVM and DBSCAN. Among them, IsoForest proved to be the best-performing algorithm, effectively removing anomalies without hyperparameter adjustment. Furthermore, IsoForest, combined with two-cluster K-means, eliminated both soil data and anomalies while preserving nearly all normal data. This strategy provides an efficient solution to reduce manual cleaning effort and enable the creation of large-scale, high-quality datasets for machine learning analysis of ID data.

Measurement While Drilling (MWD) systems require high-precision triaxial magnetometers for real-time downhole attitude sensing, yet conventional fluxgates fail to meet the stringent size, noise, bandwidth, and temperature demands of deep reservoirs (>175 °C). To bridge this gap, we present a miniaturized triaxial fluxgate magnetometer (23 × 23 × 21 mm3) leveraging Co-Fe-Si-B amorphous wire cores-a material selected for its near-zero magnetostriction and tunable magnetic anisotropy. The sensor achieves breakthrough performance: a 300 Hz bandwidth combined with noise levels below 200 pT/√Hz at 1 Hz when operating at 175 °C while maintaining full functionality with the probe surviving temperatures exceeding 200 °C. This advancement paves the way for more accurate wellbore positioning and steering in high-temperature hydrocarbon and geothermal reservoirs.

Summary Deep and ultra-deep wells are characterized by extreme temperature and pressure conditions, which significantly complicate wellbore flow and heat transfer processes. Precise determination of the convective heat transfer coefficient (CHTC) is essential for reliably forecasting wellbore temperature profiles. However, the CHTC assumed in the traditional wellbore temperature prediction model is a fixed value, ignoring the influence of changes in flow conditions (such as flow type on the CHTC), making it difficult to achieve fine prediction and update of the wellbore temperature profile. In this paper, we construct a CHTC calibration and wellbore temperature dynamic update model based on the unscented Kalman filter (UKF) algorithm. Mathematical models of different heat transfer control bodies are constructed based on the energy conservation equation. The governing equations are discretized using the finite difference method, and the Gauss-Seidel iteration is used to solve them collectively to obtain the wellbore temperature distribution. Field-measured data of three real wells are used to validate the proposed model, and the mean relative errors (MREs) of the bottomhole temperature (BHT) and outlet temperature (OLT) are less than 5%. Furthermore, based on the actual measurement while drilling (MWD) data, the UKF algorithm is used to correct the CHTC profile in the annulus, and the wellbore temperature profiles are dynamically updated in real time. The validation results indicate that the dynamic calibration model achieves a MRE of 0.21% and a mean absolute error (MAE) of 0.34°C in BHT prediction. The wellbore temperature dynamic update model proposed in this paper provides a novel method for accurate prediction of wellbore temperature.

Abstract The measurement-while-drilling (MWD) method of roof bolter plays an important role in explaining the structure of roadway roof, especially the soft hard relationship of rock layers. One of the key factors for the MWD method of roof bolter is to ensure the accuracy of monitoring, which greatly depends on the optimized selection and matching of indexes. Therefore, this study first analyzed the source of monitoring indexes data to see how they relate to normal distribution, and then evaluated their reliability for subsequent feedback.
After that, the receiver operating characteristics (ROC) quantitative calculation and analysis method was used to obtain the specific accuracy values of commonly used individual indexes and comprehensive index of specific energy. The quantitative results showed that the performances of individual thrust and torque indexes were relatively excellent, and unexpectedly exceeded that of the comprehensive index of specific energy. The research results have important reference value for the subsequent selection of MWD indexes for roof bolter. It is necessary to use indexes with better feedback results to comprehensively reflect the medium, and to furthermore improve the accuracy of feedback.

This paper presents a comprehensive study of torsional stick–slip vibrations in rotary drilling systems through a comparison between two lumped parameter models with differing complexity: a simple two-degree-of-freedom (2-DOF) model and a complex high-degree-of-freedom (high-DOF) model. The two models are developed under identical boundary conditions and consider an identical nonlinear friction torque dynamic involving the Stribeck effect and dry friction phenomena. The high-DOF model is calculated with the Finite Element Method (FEM) to enable accurate simulation of the dynamic behavior of the drill string and accurate representation of wave propagation, energy build-up, and torque response. Field data obtained from an Algerian oil well with Measurement While Drilling (MWD) equipment are used to guide modeling and determine simulations. According to the findings, the FEM-based high-DOF model demonstrates better performance in simulating basic stick–slip dynamics, such as drill bit velocity oscillation, nonlinear friction torque formation, and transient bit-to-surface contacts. On the other hand, the 2-DOF model is not able to represent these effects accurately and can lead to inappropriate control actions and mitigation of vibration severity. This study highlights the importance of robust model fidelity in building reliable real-time rotary drilling control systems. From the performance difference measurement between low-resolution and high-resolution models, the findings offer valuable insights to optimize drilling efficiency further, minimize non-productive time (NPT), and improve the rate of penetration (ROP). This contribution points to the need for using high-fidelity models, such as FEM-based models, in facilitating smart and adaptive well control strategies in modern petroleum drilling engineering.

Measurement While Drilling (MWD) technology plays a significant role in enhancing the geological steering and subsurface evaluation capabilities of extended-reach wells, challenging horizontal wells, and multilateral wells. With the increasing complexity of underground exploration, there is a heightened demand for the continuous wave mud pulse data transmission capacity. To address the inter-symbol interference(ISI) caused by the inherent inertia of the motor during high-speed data transmission using traditional modulation methods such as Frequency Shift Keying (FSK) and Phase Shift Keying (PSK), a novel approach has been proposed. This method employs Continuous Gradation Frequency Keying (CGFK) modulation combined with Convolution Neural Network (CNN) demodulation for continuous mud pulse data transmission. By controlling the waveform frequency to uniformly increase from zero to a predetermined value and then uniformly decrease back to zero within a symbol period, and utilizing the rate of frequency change as the feature for modulation and demodulation, this method effectively mitigates the issue of ISI caused by the motor’s inability to rapidly switch to the next speed due to its inertia during symbol transitions. Simulation tests indicate that, compared to the traditional Matched Filter method, Support Vector Machine (SVM), Long Short-Term Memory (LSTM) networks, and CNN exhibit superior performance in recognizing CGFK, with CNN demonstrating the best results. Physical tests show that CGFK, particularly when assisted by CNN demodulation, possesses the capability to avoid or reduce ISI caused by motor inertia, and achieves favorable information transmission rates and bit error rate (BER) compared to traditional FSK and PSK.

The high temperature resistance of measurement while drilling (MWD) instruments hinders the development of drilling technology. This article adopts a turbine driven refrigeration power system to overcome the problem of difficulty in inputting external energy during the cooling process of the refrigerator. Adopting a regenerative refrigeration system to reduce the impact of the radiator on the circuit compartment. We design active cooling systems with sidewall cabin and central water eye, and studied their heat transfer characteristics using numerical methods based on Fluent 21.0. The research results indicate that the central water eye active cooling system has better heat resistance performance and a lower heat load of 8.65 W for the refrigeration unit. For the central water eye type, reducing the surface radiation coefficient of the parts results in less external heat leakage change.

This research investigates the role of big data analytics and machine learning in optimizing drilling operations, with a specific focus on predicting optimal drilling parameters to mitigate unplanned downtime (UDT). Conducted over two years at various oil drilling sites in Canada, the study highlights the integration of Logging While Drilling (LWD) and Measurement While Drilling (MWD) data into predictive models. The findings demonstrate a significant reduction in UDT through the development of machine learning algorithms that analyze historical drilling data to forecast and optimize the Rate of Penetration (ROP). Despite the advancements, challenges such as real-time data integration and anomaly detection were identified, emphasizing the need for enhanced data quality and management frameworks. The implications of this research underscore the necessity for drilling companies to adopt data-driven strategies and invest in workforce training to fully realize the potential of predictive analytics. By providing actionable insights, this study contributes to the ongoing evolution of drilling practices, paving the way for more efficient and resilient ope rations in the oil and gas industry.

With the increasing availability of computational resources, machine learning (ML) has become a significant and rapidly growing technology. By leveraging geological uncertainties and machine learning techniques, drilling and blasting can be re-focussed from a bulk mining operation to more selective, precise and efficient extraction for ore preconcentration techniques and mine to mill optimisation in critical metal mining and/or lump-to-fine optimisation for iron ore extraction. While ML can have a notable impact on open-pit drilling and blasting, training ML models with small exploration datasets or noisy production data is challenging. To leverage the often limited and noisy data with the aim of improving the accuracy of ML models, this paper presents a generative transformer (i.e. TTS-CGAN)-assisted recurrent neural network (RNN) methodology to better understand the variability of blastability index (BI) extracted from the fusion of measurement while drilling (MWD) data (strength and fracture percentage) with rock density from assay information, on a bench scale. An implementation of the proposed method at a platinum mine and an iron ore deposit shows that mixing a small amount of augmented data with real data is beneficial for RNN performance. However, an optimal point exists as the addition of too much synthetic data may introduce additional noise.

Abstract Accurate lithology classification is essential as variations in rock formations can significantly impact the cost and efficiency of mineral exploration and mining. Initial exploration maps provide insights into subsurface formations, though typically collected at widely spaced intervals. This study examines the use of early exploration data and Measurement While Drilling (MWD) data for lithology prediction through machine learning. The research specifically evaluates the benefit of incorporating spatial coordinates with MWD parameters to enhance classification accuracy, using support vector machine (SVM), random forest (RF), and extra gradient boosting (XGBoost) classifiers with tenfold cross-validation. The models were trained on 235,501 data points of six MWD parameters from 308 drill holes. The effects of raw (imbalanced) versus Synthetic Minority Oversampling Technique combined with Edited Nearest Neighbor (SMOTEENN) (balanced) data were analyzed, along with a comparison between random and spatial data splits. Results indicate that SMOTEENN-balanced data paired with a spatial split strategy consistently improved model stability, with the XGBoost model achieving the highest performance, with a precision of 95.60% and an F1 score of 94.41% on unseen data. Additionally, the study revealed that integrating spatial coordinates of drilling locations consistently enhanced lithology classification, with a notable F1 score improvement of 27.97% using XGBoost. The findings highlight the value of combining spatial coordinates and MWD data for improved lithology classification and offer potential support for geological modeling and sustainable mining practices.

Abstract Directional drilling machines are extensively employed in gas drainage, water exploration, and coalbed methane exploration in underground coal mines. The measurement while drilling (MWD) system collects the spatial orientation and depth parameters of the drill rod during the drilling process using a three-axis sensor, which guides the drill rod along the predefined trajectory, ensuring it reaches the designated drilling position for safe coal mining. Due to installation angle errors of the three-axis sensor and alignment discrepancies between sensors, the sensor produces complex three-dimensional spatial errors during measurement, complicating the identification of the physical plane correction axis needed for traditional installation error correction methods. To resolve this issue, a BP neural network-based correction algorithm for installation errors in the MWD system is proposed. The algorithm disregards installation errors of accelerometer and magnetometer sensors, does not necessitate additional parameter calculations, and directly predicts attitude angles through ellipsoid fitting of the measurement data, thereby effectively mitigating the impact of installation errors. The effectiveness and prediction accuracy of the algorithm are validated through numerical model experiments, ground experiments, and underground tests. The results demonstrate that the absolute azimuth error in the indoor experiment is less than 1°, improving by approximately 5° compared to the traditional scalar product constant method, with an absolute pitch angle error of 0.1°, improving by approximately 1.5° compared to the traditional plane-fitting method. The absolute azimuth error in the ground experiment is less than ±1.8°, and the absolute pitch angle error is less than ±0.18°, which meets the requirements of the while-drilling measurement system for underground coal mining projects.

In geotechnical engineering, an accurate prediction is essential for the safety and effectiveness of construction projects. One example is the prediction of over/under-excavation volumes during drill and blast tunneling. Using machine learning (ML) models to predict over-excavation often results in low accuracy, especially in complex geological settings. This study explores how the pre-processing of measurement while drilling (MWD) data impacts the accuracy of ML models. In this work, a correlational analysis of the MWD data is used as the main pre-processing procedure. For each drilling event (single borehole), correlation coefficients are calculated and then supplied as inputs to the ML model. It is shown that the ML model’s accuracy improves when the correlation coefficients are used as inputs to the ML models. It is observed that datasets made from correlation coefficients help ML models to obtain higher generalization skills and robustness. The informational content of datasets after different pre-processing routines is compared, and it is shown that the correlation coefficient dataset retains information from the original MWD data.

The attitude angles of the drilling tool serve as crucial information for transmitting Measurement While Drilling (MWD) data, enabling the optimization of drilling performance and ensuring tool safety. However, the real-time transmission and processing of attitude data pose a significant challenge, especially with the increasing prevalence of horizontal and directional drilling. To accurately and promptly obtain the attitude data, this paper proposes a lossless compression method based on Huffman coding, called Adaptive Frame Prediction Huffman Coding (AFPHC). This approach leverages the slowly varying characteristics of MWD tool attitude data, employing frame residual prediction to reduce data volume and selecting optimal bit widths for encoding transmission data. By using real-world drilling data, the proposed method is implemented on a Verilog HDL on a Xilinx field-programmable gate array (FPGA) circuit. Simulation and experiment results show that compression ratios provided by the proposed method for the inclination, azimuth, and toolface angles reach up to 4.02 times, 3.98 times, and 1.48 times, respectively, outperforming several existing methods.

For Measurement While Drilling (MWD), the redundant Micro-Electro-Mechanical Systems Inertial Measurement Unit (MEMS-IMU) navigation system significantly enhances the reliability and accuracy of drill string attitude measurements. Such an enhancement enables precise control of the wellbore trajectory and enhances the overall quality of drilling operations. But installation errors of the redundant MEMS-IMUs still degrade the accuracy of drill string attitude measurements. It is essential to calibrate these errors to ensure measurement precision. Currently, the commonly used calibration method involves mounting the carrier on a horizontal plane and performing calibration through rotation. However, when the carrier rotates on the horizontal plane, the gravity acceleration component sensed by the horizontal axis of the IMU accelerometer in the carrier is very small, which leads to a low signal-to-noise ratio, so that the measured matrix obtained by the solution is dominated by noise. As a result, the accuracy of the installation is insufficient, and, finally, the effectiveness of the installation error compensation is reduced. In order to solve this problem, this study proposes a 45°-inclined six-position calibration method based on the selected hexagonal prism redundant structure for redundant MEMS-IMUs in MWD. Firstly, the compensation matrices and accelerometer measurement errors were analyzed, and the new calibration method was proposed; the carrier of the IMUs should be installed at an inclined position of 45°. Then, six measuring points were identified for the proposed calibration approach. Finally, simulation and laboratory experiments were conducted to verify the effectiveness of the proposed method. The simulation results showed that the proposed method reduced installation errors by 40.4% compared with conventional methods. The experiments' results demonstrated reductions of 83% and 68% in absolute measurement errors for the x and y axes, respectively. As a result, sensor accuracy after compensation improved by over 25% compared with traditional methods. The calibration method proposed by this study effectively improves the accuracy of redundant systems, providing a new approach for the precise measurement of downhole trajectories.

This study presents an application of Boruta-SHapley Additive ExPlanations (Boruta-SHAP) for geotechnical characterization using Measure-While-Drilling (MWD) data, enabling a more interpretable and statistically rigorous assessment of feature importance. Measure-While-Drilling data collected at the scale of an open-pit mine was used to characterize geotechnical properties using regression-based machine learning models. In contrast to previous studies using MWD data to recognize rock type using Principal Component Analysis (PCA), which only identifies the directions of maximum variance, the Boruta-SHAP method quantifies the individual contribution of each Measure-While-Drilling variable. This method ensures interpretable and reliable geotechnical characterization as well as robust feature selection by comparing predictors against randomized ‘shadow’ features. The Boruta-SHAP analysis revealed that bit air pressure and torque-to-penetration ratio were the most significant predictors of rock strength, contradicting previous assumptions that rate of penetration was the dominant factor. Moreover, feature importance was conducted for fracture frequency and Geological Strength Index (GSI), a rock mass classification system. A comparative analysis of prediction performance was also performed using a range of different machine learning algorithms that resulted in strong coefficient of determinations of actual field or laboratory results versus predicted values. The results are plausible, confirming that MWD data could provide a high-resolution description of geotechnical conditions prior to mining, leading to a more confident prediction of subsurface geotechnical properties. Therefore, the fragmentation from blasting as well as downstream operational phases, such as digging, hauling, and crushing, could be improved effectively.

Extracting rock mass strength properties from existing data like Measurement While Drilling (MWD) is important to reduce the cost of additional geological and geotechnical surveys. This study presents an approach that combines clustering (unsupervised learning) and classification algorithms to identify similar rock groups for their prediction. The dataset comprises 272,272 MWD from 2,790 drill holes, split into 215,401 data points (2,332 drill holes) for cross-validation, and another 215,401 data points, from 558 previously unseen drill holes for testing. Principal component analysis (PCA) and clustering algorithms such as K-means, Gaussian mixture, C Fuzy, and hierarchical clustering were employed to group rocks with similar MWD parameters. The combination of PCA and k-means clustering provides good cluster quality which best describes the different rock strength characteristics (clusters), as revealed by geological investigation and coring data. After identifying the rock categories, Extra Gradient Boosting (XGBoost), and Adaptive Boosting (AdaBoost) approaches were used to develop classification models for rock strength prediction. The XGBoost model achieved the best and most reliable performance with accuracy, precision, recall, and F1 score exceeding 98% on the test set. This study highlights the synergetic benefits of combining unsupervised and supervised machine learning techniques to predict rock mass conditions, especially in scenarios with limited geological information or unavailable labeled data.

Bench-scale geotechnical characterization often suffers from high uncertainty, reducing confidence in geotechnical analysis on account of expensive resource development drilling and mapping. The Measure-While-Drilling (MWD) system uses sensors to collect the drilling data from open-pit blast hole drill rigs. Historically, the focus of MWD studies was on penetration rates to identify rock formations during drilling. This study explores the effectiveness of Artificial Intelligence (AI) classification models using MWD data to predict geotechnical categories, including stratigraphic unit, rock/soil strength, rock type, Geological Strength Index, and weathering properties. Feature importance algorithms, Minimum Redundancy Maximum Relevance and ReliefF, identified all MWD responses as influential, leading to their inclusion in Machine Learning (ML) models. ML algorithms tested included Decision Trees, Support Vector Machines (SVMs), Naive Bayes, Random Forests (RFs), K-Nearest Neighbors (KNNs), Linear Discriminant Analysis. KNN, SVMs, and RFs achieved up to 97% accuracy, outperforming other models. Prediction performance varied with class distribution, with balanced datasets showing wider accuracy ranges and skewed datasets achieving higher accuracies. The findings demonstrate a robust framework for applying AI to real-time orebody characterization, offering valuable insights for geotechnical engineers and geologists in improving orebody prediction and analysis