Lost circulation, a common risk during the drilling process, significantly impacts drilling safety and efficiency. The presence of data noise and temporal evolution characteristics pose significant challenges to the accurate monitoring of lost circulation. Traditional supervised intelligent monitoring methods rely on large amounts of labeled data, which often do not consider temporal fluctuations in data, leading to insufficient accuracy and transferability. To address these issues, this paper proposes an unsupervised time series autoencoder (BiLSTM-AE) intelligent monitoring model for lost circulation, aiming to overcome the limitations of supervised algorithms. The BiLSTM-AE model employs BiLSTM for both the encoder and decoder, enabling it to comprehensively capture the temporal features and dynamic changes in the data. It learns the patterns of normal data sequences, thereby automatically identifying anomalous risk data points that deviate from the normal patterns during testing. Results show that the proposed model can efficiently identify and monitor lost circulation risks, achieving an accuracy of 92.51%, a missed alarm rate of 6.87%, and a false alarm rate of 7.71% on the test set. Compared to other models, the BiLSTM-AE model has higher accuracy and better timeliness, which is of great significance for improving drilling efficiency and ensuring drilling safety.

Deep and offshore drilling operations face complex geological formations, uncertain formation pressures, and narrow safety density windows, making them susceptible to lost circulation risks. To address these challenges, this paper introduces an innovative, intelligent lost circulation monitoring model that incorporates geological lithology information. This model not only utilizes real-time drilling parameters, but also encodes geological information such as rock type as inputs to the model. By combining these key lithological features, the model can comprehensively assess wellbore stability and reduce the lost circulation risks. In this paper, the Conditional Tabular Generative adversarial network (CTGAN) model is used to enhance the data of small-sample risk data, which can effectively expand the data distribution space and improve the performance of the model. This paper conducts a comparative analysis of intelligent monitoring results using artificial neural networks (ANNs), long short-term memory (LSTM), and temporal convolutional networks (TCNs). The results show that the TCN achieves an identification accuracy of 93.7%. Furthermore, the analysis reveals that the inclusion of lithology information significantly enhances the model’s performance, resulting in a 7.1% increase in accuracy. The false alarm rate of the model can be reduced by 10.2%, considering the fluctuation of the logging curve caused by the on/off condition of the pump. This indicates that the introduction of lithology information and the condition of the pump on−off provide advantages in monitoring and identifying lost circulation risks, enabling a more precise assessment of wellbore stability and a reduction in lost circulation incidents. The method of lost circulation monitoring proposed in this paper provides an important safety guarantee for the oil drilling industry.

As oil and gas exploration and development gradually advance into deeper and offshore fields, the geological environment and formation pressure conditions become increasingly complex, leading to a higher risk of drilling incidents such as kicks. Timely diagnosis of kick risk is crucial for ensuring safety and efficiency. This study proposes a kick risk diagnosis method based on ensemble learning models, which integrates various time-series analysis algorithms to construct and optimize multiple kick diagnosis models, accurately fitting the relationship between integrated logging parameters and kick events. By incorporating high-performance ensemble models such as Stacking and Bagging, the accuracy and F1 score of the models were significantly improved. Furthermore, the application of the Synthetic Minority Over-sampling Technique and Tomek Links (SMOTE-Tomek) data balancing technique effectively addressed the issue of data imbalance, contributing to a more robust and balanced model performance. The results demonstrate that integrating time-series analysis with ensemble learning methods significantly enhances the predictive reliability and stability of kick monitoring models. This approach provides a dependable solution for addressing complex kick monitoring tasks in offshore and deepwater drilling operations, ensuring greater safety and efficiency. The findings offer valuable insights that can guide future research and practical implementation in kick risk diagnosis.

Managed pressure drilling (MPD) is the core technology for developing formations with high pressure and narrow density windows. It precisely maintains the bottomhole pressure (BHP) within the safe operating window defined by formation pore pressure and fracture pressure by actively regulating the wellbore pressure profile. If pressure control becomes unstable, it can easily trigger gas kicks or lost circulation, posing a severe threat to operational safety. However, existing model predictive control (MPC) schemes have significant limitations: pure data-driven models exhibit poor generalization under complex conditions, while control algorithms based on traditional mechanistic models struggle to meet the stringent real-time requirements of field control cycles due to high-complexity numerical iteration processes. To balance control precision and real-time performance, this paper proposes a physics-informed model predictive control framework (PINC-MPC). During the training phase, physical prior knowledge such as the law of mass conservation is embedded into the neural network as constraints to construct a physically consistent deep surrogate model, enabling it to characterize complex wellbore characteristics. In the control phase, this surrogate model replaces the time-consuming numerical solving process of the mechanistic model within the MPC loop, achieving near-real-time state prediction and rolling optimization while ensuring physical fidelity. Experimental results indicate that PINC-MPC demonstrates superior control performance. Its median single-step solving time is only 16.81 ms, achieving an 11.1-fold acceleration compared to the mechanistic model-based scheme (187.3 ms). In a 5000 s full-cycle closed-loop control experiment, the total time required for the former is only 1.68 s, while the latter reaches 18.73 s, representing an efficiency improvement of approximately 91%. In terms of control accuracy, the integrated absolute error (IAE), reflecting the total deviation of the control process, significantly decreased from 63.40 MPa·s for the industrial successive linearization MPC (SLMPC) to 12.90 MPa·s, an improvement of 79.7%. Especially in extreme dynamic conditions such as simulated pump shutdowns for pipe connections and sudden gas kicks, the framework demonstrates excellent predictive ability and response efficiency. It can proactively trigger compensation actions to keep BHP fluctuations within 0.30 MPa, significantly outperforming the traditional SLMPC method. The research results prove that PINC-MPC provides an efficient, precise, and robust nonlinear control strategy for MPD systems, offering important engineering reference value for enhancing the automation level of intelligent drilling systems.

Lost circulation is a major challenge in the drilling process, which seriously restricts the safety and efficiency of drilling. The traditional monitoring model is hindered by the presence of noise and the complexity of temporal fluctuations in lost circulation data, resulting in a suboptimal performance with regard to accuracy and generalization ability, and it is not easy to adapt to the needs of different working conditions. To address these limitations, this study proposes a multi-scale feature fusion model based on wavelet transform and TimeGAN. The wavelet transform enhances the features of time series data, while TimeGAN (Time Series Generative Adversarial Network) excels in generating realistic time series and augmenting scarce or missing data. This model uses convolutional network feature extraction and a multi-scale feature fusion module to integrate features and capture time sequence information. The experimental findings demonstrate that the multi-scale feature fusion model proposed in this study enhances the accuracy by 8.8%, reduces the missing alarm rate and false alarm rate by 12.4% and 6.2%, respectively, and attains a test set accuracy of 93.8% and precision of 95.1% in the lost circulation identification task in comparison to the unoptimized model. The method outlined in this study provides reliable technical support for the monitoring of lost circulation risk, thereby contributing to the enhancement of safety and efficiency in the drilling process.