Weibin Cheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Weibin Cheng has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Shaobing Hu
College of Geophysics and Petroleum Resources, Yangtze University, Wuhan, China
4 shared publications Tao Guo
2 shared publications- Yifei Zhang
School of Electronic Information and Electrical Engineering, Yangtze University, Jingzhou 434023, China
2 shared publications Zhuoran Meng
2 shared publications- Gong Zhang
College of Geophysics and Petroleum Resources, Yangtze University, Wuhan 430100, China
1 shared publication Haoran Meng
China national logging corporation CNLC, Xi’an City, Shaanxi Province, China
1 shared publication
Latest Publications
- 24 June 2026
- Published by Elsevier in Measurement
- Vol. 285
High-precision geo-orientation in MWD systems via tumble optimized accelerometer calibration
- 24 June 2026
- Published by Elsevier in Measurement
- Vol. 285
High-precision geo-orientation in MWD systems via tumble optimized accelerometer calibration
- Open Access
- 29 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 135806-135821
An XGBoost-SHAP Model for Energy Demand Prediction With Boruta–Lasso Feature Selection
Energy demand prediction is essential in ensuring national energy security, promoting high-quality economic development, advancing sustainable development, optimizing the energy structure, and achieving dual carbon goals. In recent years, machine learning (ML) algorithms have been extensively used in energy demand prediction but with poor interpretability. This study proposes an interpretable ML framework for energy demand prediction based on the Boruta-Lasso two-stage feature selection model, extreme gradient boosting (XGBoost) regression model, grid search optimization algorithm, and Shapley additive explanations (SHAP) algorithm. Taking China as an example, the results show that the XGBoost-based model achieves R2, MAE, and RMSE of 0.9975, 0.0108, and 0.0157, respectively, with higher prediction accuracy compared to other models. In addition, the analysis based on the SHAP algorithm shows that gross national income (GNI), gross domestic product (GDP), total population at the year-end, per capita consumption expenditure, and the proportion of added value of the secondary industry are the main drivers of energy demand. The framework established in this study helps to screen influencing factors, predict energy demand, and simultaneously explain the relationship between these factors and energy demand.
- 29 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 135806-135821
Open AccessAn XGBoost-SHAP Model for Energy Demand Prediction With Boruta–Lasso Feature Selection
Energy demand prediction is essential in ensuring national energy security, promoting high-quality economic development, advancing sustainable development, optimizing the energy structure, and achieving dual carbon goals. In recent years, machine learning (ML) algorithms have been extensively used in energy demand prediction but with poor interpretability. This study proposes an interpretable ML framework for energy demand prediction based on the Boruta-Lasso two-stage feature selection model, extreme gradient boosting (XGBoost) regression model, grid search optimization algorithm, and Shapley additive explanations (SHAP) algorithm. Taking China as an example, the results show that the XGBoost-based model achieves R2, MAE, and RMSE of 0.9975, 0.0108, and 0.0157, respectively, with higher prediction accuracy compared to other models. In addition, the analysis based on the SHAP algorithm shows that gross national income (GNI), gross domestic product (GDP), total population at the year-end, per capita consumption expenditure, and the proportion of added value of the secondary industry are the main drivers of energy demand. The framework established in this study helps to screen influencing factors, predict energy demand, and simultaneously explain the relationship between these factors and energy demand.
- 23 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-9
Enhanced Azimuth Determination in Drilling via Piecewise Polynomial Fitting and Interpolation
Precise geomagnetic azimuth measurement is essential for automation and intelligent operations in deep-earth and deep-sea resource exploration. However, during drilling, the main sources of azimuth error include the inherent distortion of triaxial accelerometer and triaxial magnetometer, which require prior calibration. To address this issue, we focus on static azimuth measurements by analyzing the error propagation relationship, developing a comprehensive error correction model, and proposing a correction method that combines piecewise polynomial fitting and improved interpolation. Finally, the proposed algorithm was experimentally validated using a high-precision inclinometer calibration platform. The experiment compared the error correction effects of the three-step combination method and the proposed method. At a confidence level of p =0.95 and an axial tilt of I =0.594, dA decreased from (3.1° ± 0.9°) to (1.8° ± 0.5°) and (7*10 -4 ° ± 3.7*10 -2 °) for the traditional and proposed method, respectively. The proposed method demonstrates good performance in azimuth reconstruction and meets the practical engineering demands of azimuth calibration in measurement-while-drilling system.
- 23 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-9
Enhanced Azimuth Determination in Drilling via Piecewise Polynomial Fitting and Interpolation
Precise geomagnetic azimuth measurement is essential for automation and intelligent operations in deep-earth and deep-sea resource exploration. However, during drilling, the main sources of azimuth error include the inherent distortion of triaxial accelerometer and triaxial magnetometer, which require prior calibration. To address this issue, we focus on static azimuth measurements by analyzing the error propagation relationship, developing a comprehensive error correction model, and proposing a correction method that combines piecewise polynomial fitting and improved interpolation. Finally, the proposed algorithm was experimentally validated using a high-precision inclinometer calibration platform. The experiment compared the error correction effects of the three-step combination method and the proposed method. At a confidence level of p =0.95 and an axial tilt of I =0.594, dA decreased from (3.1° ± 0.9°) to (1.8° ± 0.5°) and (7*10 -4 ° ± 3.7*10 -2 °) for the traditional and proposed method, respectively. The proposed method demonstrates good performance in azimuth reconstruction and meets the practical engineering demands of azimuth calibration in measurement-while-drilling system.
- 19 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (20) , 31816-31826
Piecewise In-Plane Calibration for Drilling Inclinometer System
Tilt measurement is commonly achieved by sensing the gravity, its accuracy heavily depends on the calibration procedure. This paper investigates accelerometer calibration scheme of a drilling inclinometer, and proposes a novel piecewise in-plane calibration scheme to update the calibration coefficients from the results of the ellipsoid fitting (EF) and the plane fitting (PF). According to the motions rotating around the inclinometer frame, the proposed scheme utilizes the maximum likelihood to estimate the adjustment for calibration coefficient, as a modification to the EF+PF scheme. The simulation and experimental results demonstrate that, compared to existing methods in drilling application, the proposed scheme significantly reduces the error of tilt measurement. Specifically, the proposed inclinometer system achieves an error of less than −0.0011±0.0108° (1σ) for the axial tilt angle and less than −0.0931±0.0735° (1σ) for the tool face angle.
- 19 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (20) , 31816-31826
Piecewise In-Plane Calibration for Drilling Inclinometer System
Tilt measurement is commonly achieved by sensing the gravity, its accuracy heavily depends on the calibration procedure. This paper investigates accelerometer calibration scheme of a drilling inclinometer, and proposes a novel piecewise in-plane calibration scheme to update the calibration coefficients from the results of the ellipsoid fitting (EF) and the plane fitting (PF). According to the motions rotating around the inclinometer frame, the proposed scheme utilizes the maximum likelihood to estimate the adjustment for calibration coefficient, as a modification to the EF+PF scheme. The simulation and experimental results demonstrate that, compared to existing methods in drilling application, the proposed scheme significantly reduces the error of tilt measurement. Specifically, the proposed inclinometer system achieves an error of less than −0.0011±0.0108° (1σ) for the axial tilt angle and less than −0.0931±0.0735° (1σ) for the tool face angle.
- 8 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 70 (00189456) , 1-9
Near-Vertical Attitude Determination Based on Balance Correction
At the near-vertical position, the system error is a major factor lowering the attitude accuracy in the attitude determination system, and correction technology is often used to compensate all kinds of system errors. First, the absolute errors of the computed attitude angle including the measurement error and the correction error are analyzed, and the correction error caused by the correction matrix is emphatically derived and discussed. Then, a novel balance correction method with a nonunit correction matrix is proposed and verified theoretically. Finally, an inertial measurement unit (IMU) is tested for the near-vertical position and corrected with the conventional unit matrix and the proposed balance correction. The experimental results suggest that the balance correction under the near-vertical position can enhance the accuracies of the attitude angles over four times than those with the conventional correction.
- 8 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 70 (00189456) , 1-9
Near-Vertical Attitude Determination Based on Balance Correction
At the near-vertical position, the system error is a major factor lowering the attitude accuracy in the attitude determination system, and correction technology is often used to compensate all kinds of system errors. First, the absolute errors of the computed attitude angle including the measurement error and the correction error are analyzed, and the correction error caused by the correction matrix is emphatically derived and discussed. Then, a novel balance correction method with a nonunit correction matrix is proposed and verified theoretically. Finally, an inertial measurement unit (IMU) is tested for the near-vertical position and corrected with the conventional unit matrix and the proposed balance correction. The experimental results suggest that the balance correction under the near-vertical position can enhance the accuracies of the attitude angles over four times than those with the conventional correction.