An axial piston pump fault diagnosis algorithm based on empirical wavelet transform (EWT) and one‐dimensional convolutional neural network (1D‐CNN) is presented. The fault vibration signals and pressure signals of axial piston pump are taken as the analysis objects. Firstly, the original signals are decomposed by EWT, and each signal component is screened and reconstructed according to the energy characteristics. Then, the time‐domain features and the frequency‐domain features of the denoised signal are extracted, and features of time domain and frequency domain are fused. Finally, the 1D‐CNN model was deployed to the WISE‐Platform as a Service (WISE‐PaaS) cloud platform to realize the real‐time fault diagnosis of axial piston pump based on the cloud platform. Compared with ensemble empirical mode decomposition (EEMD) and complementary ensemble empirical mode decomposition (CEEMD), the results show that the axial piston pump fault diagnosis algorithm based on EWT and 1D‐CNN has higher fault identification accuracy.

Hydraulic pumps are commonly used; however, it is difficult to predict their remaining useful life (RUL) effectively. A new method based on kernel principal component analysis (KPCA) and the just in time learning (JITL) method was proposed to solve this problem. First, as the research object, the non-substitute time tac-tail life experiment pressure signals of gear pumps were collected. Following the removal and denoising of the DC component of the pressure signals by the wavelet packet method, multiple characteristic indices were extracted. Subsequently, the KPCA method was used to calculate the weighted fusion of the selected feature indices. Then the state evaluation indices were extracted to characterize the performance degradation of the gear pumps. Finally, an RUL prediction method based on the k-vector nearest neighbor (k-VNN) and JITL methods was proposed. The k-VNN method refers to both the Euclidean distance and angle relationship between two vectors as the basis for modeling. The prediction results verified the feasibility and effectiveness of the proposed method. Compared to the traditional JITL RUL prediction method based on the k-nearest neighbor algorithm, the proposed prediction model of the RUL of a gear pump presents a higher prediction accuracy. The method proposed in this paper is expected to be applied to the RUL prediction and condition monitoring and has broad application prospects and wide applicability.

This paper presents an integrated downhole risk prevention and control system designed to enhance safety, efficiency and sustainability in deep-well drilling operations. The system incorporates advanced measurement processing, risk evaluation, and intelligent data transmission technologies for real-time monitoring of nine key drilling parameters, such as downhole drilling pressure, bending moment, and torque, etc. Bench tests and field trials demonstrated the system’s reliability in accurately capturing and transmitting data under high-pressure, high-temperature conditions. For instance, it successfully monitored bottom-hole pressure up to 61.4 MPa and temperature to 120.8 °C, allowing for early detection of abnormal events such as pressure kicks and torsional stick-slip. The system was laboratory-tested to withstand bottom-hole pressures up to 61.4 MPa and temperatures of 120.8 °C. During field trials, the tool operated safely under actual downhole conditions of approximately 59.2 MPa and 115 °C, which are within its rated limits. The system also facilitated automated controlled actions, including mud weight and pump rate control, to prevent incidents. These results underscore the system’s potential to significantly improve real-time and intelligent process control, minimize operational risks, and advancing the sustainability of drilling practices. The approach marks a step forward in intelligent drilling technologies, supporting proactive decision-making in energy extraction. Future work will extend this system to ultra-deep and high-temperature wells while integrating advanced AI-based analytics for further optimization.

During deep and ultra-deep oil and gas drilling, downhole high-temperature and high-pressure conditions significantly affect the measurement accuracy of piezoresistive pressure sensors. To improve measurement accuracy under such extreme conditions, this study proposes an intelligent temperature compensation method based on a Modified Slime Mold Algorithm (MSMA). An experimental platform covering the full operating range of 0–175 °C and 0–170 MPa was established to acquire sensor outputs, and samples were collected at various temperature and pressure points to construct a dataset. Key parameters of the compensation model were optimized using the MSMA, enhancing the model’s fitting capability. Results indicate that, after compensation, the sensor exhibits a maximum full-scale error of 0.26% and a maximum sensitivity drift of −0.019% FS/°C, significantly reducing errors compared with traditional interpolation and polynomial fitting methods. The optimized compensation model was further deployed on an embedded hardware platform, enabling high-precision temperature compensation in an engineering context. Experimental data demonstrate that the embedded implementation maintains compensation accuracy while meeting real-time application requirements, making it suitable for downhole pressure monitoring and for output correction of other intelligent sensors operating under complex field conditions.

Measurement While Drilling (MWD) tools are widely employed in deep and ultra-deep well drilling. In the high-temperature and high-pressure (HTHP) environments characteristic of these wells, structural deformation induced by thermal expansion interferes with the bit parameter recorder’s sensor readings, thereby degrading the measurement accuracy of weight on bit (WOB) and working torque (WT). To address this issue, this paper proposes a temperature compensation method based on thermo-mechanical coupling simulation. This method systematically establishes the quantitative relationships between multiple loads—including WT, WOB, temperature, and make-up torque—and the strain at critical locations of the bit parameter recorder through finite element analysis (FEA). Furthermore, surface calibration experiments have verified a strong linear correlation between the strain gauge voltage signals and the simulated strain. Building upon this foundation, an inversion-based compensation algorithm is developed. This algorithm effectively isolates the interference caused by thermally induced deformation and inversely deduces the true WOB and torque values by utilizing downhole-measured sensor voltage and temperature data. The research results demonstrate that the proposed temperature compensation method significantly improves the measurement accuracy of the bit parameter recorder under harsh, high-temperature operating conditions. The relative errors for both WOB and torque measurements are controlled to within 5%, providing a reliable solution for precise parameter measurement in high-temperature deep wells.

To achieve fast and precise position servo control in a continuous-wave pulse generator and address issues such as internal and external disturbances and significant overshoot, this paper proposes an improved linear active disturbance rejection control strategy. First, a mathematical model of the permanent magnet synchronous motor is established, and a second-order linear active disturbance rejection controller is designed based on this model. To address the issue of large errors in disturbance estimation by the traditional extended state observer, a cascaded extended state observer is introduced. By designing an additional state observer to estimate the system’s residual disturbances, the impact of disturbances on system performance is further reduced. Through an in-depth analysis of the motion characteristics of the continuous-wave pulse generator, the trade-off between system overshoot and response speed is revealed. To address this, a new adaptive law is proposed. This law, based on the system’s periodic wave response and tracking error, adjusts the parameters of the linear state error feedback control law in real time, reducing system overshoot while improving response speed. To validate the effectiveness of the proposed control strategy, a simulation model of the position servo control system for the continuous-wave pulse generator was developed. The comparative analysis of the simulation results for the different control strategies shows that the improved linear active disturbance rejection control strategy significantly enhances the system’s dynamic response performance.