Formation lithology identification is of great importance for reservoir characterization and petroleum exploration. Previous methods are based on cutting logging and well-logging data and have a significant time lag. In recent years, many machine learning methods have been applied to lithology identification by utilizing well-logging data, which may be affected by drilling fluid. Drilling string vibration data is a high-density ancillary data, and it has the advantages of low-latency, which can be acquired in real-time. Drilling string vibration data is more accessible and available compared to well-logging data in ultra-deep well drilling. Machine learning algorithms enable us to develop new lithology identification models based on these vibration data. In this study, a vibration dataset is used as the signal source, and the original vibration signal is filtered by Butterworth (BHPF). Vibration time–frequency characteristics were extracted into time–frequency images with the application of short-time Fourier transform (STFT). This paper develops lithology classification models using new data sources based on a convolutional neural network (CNN) combined with Mobilenet and ResNet. This model is used for complex formation lithology, including fine gravel sandstone, fine sandstone, and mudstone. This study also carries out related model accuracy verification and model prediction results interpretation. In order to improve the trustworthiness of decision-making results, the gradient-weighted class-activated thermal localization map is applied to interpret the results of the model. The final verification test shows that the single-sample decision time of the model is 10 ms, the test macro precision rate is 90.0%, and the macro recall rate is 89.3%. The lithology identification model based on vibration data is more efficient and accessible than others. In conclusion, the CNN model using drill string vibration supplies a superior method of lithology identification. This study provides low-latency lithology classification methods to ensure safe and fast drilling.

Rate of penetration (ROP) prediction is critical for the optimization of drilling parameters and ROP improvement during drilling. However, it is still challenging to accurately predict ROP based on traditional empirical formula methods. This is usually the case for the development of the Wushi 17-2 oilfield block in the South China Sea. The Liushagang Formation is complex and the ROP is relatively low and difficult to increase. Ordinary data-driven ROP prediction models are not applicable because they do not take into account the complexity of formation conditions. In this work, we characterize the formation with acoustic transit time and build a data-driven ROP prediction model based on a deep neural network approach. By using the exploratory well data of the Wushi 17-2 oilfield for training and testing, the matching degree of the established model with the real data can reach 82%. In addition, we have developed a drilling parameter optimization process based on the ROP prediction model to improve ROP. Through on-site simulation, we found that the process can well meet the construction requirements. The established models and process flow are also applicable to the development of other formations and fields.

The hot dry rock geothermal energy is one kind of the clean energies which are contained in the China National Energy Strategy. This strategy is to encourage the development of the green and clean energy instead of the fossil energy. In the development of hot dry rock (HDR), the artificial geothermal reservoir is built through drilling and hydraulic fracturing. Two wells are drilled and connected by hydraulic fractures. Then, the geothermal energy can be extracted by the water circulation. The cold water is injected into one of the two wells and flowed along with the hydraulic fractures. The water becomes gas when it contacts the formation rock because of the high temperature. The phase change since the temperature and pressure are reduced at the wellhead of the another well can provide power to generate electricity. Therefore, the key technology to build artificial geothermal reservoir is drilling and hydraulic fracturing. However, there is few experiences in drilling and hydraulic fracturing in the HDR in China. This paper summarized and analyzed the research and field cases around the world to investigate the challenges and key points during drilling and hydraulic fracturing in the HDR. The investigation was based on geology condition, rock physics and chemistry, and field operation during the HDR development. The summary provided the common problems and experience of the drilling and hydraulic fracturing. In addition, the further research directions of related technologies were expounded. Finally, this paper could be referenced for the drilling and hydraulic fracturing in the development of HDR in China for effective utilization.

Water uptake induced by fluid–rock interaction plays a significant role in the recovery of flowback water during hydraulic fracturing. However, the existing accounts fail to fully acknowledge the significance of shale anisotropy on water uptake typically under in situ reservoir temperature. Thus we investigated the shale-hydration anisotropy using two sets of shale samples from the Longmaxi Formation in Sichuan Basin, China, which are designated to imbibe water parallel and perpendicular to shale bedding planes. All the samples were immersed in distilled water for one to five days at 80 °C or 120 °C. Furthermore, samples’ topographical and elemental variations before and after hydration were quantified using energy-dispersive spectroscopy–field-emission scanning electron microscopy. Our results show that shale anisotropy and imbibition time strongly affect the width of pre-existing micro-fracture in hydrated samples. For imbibition parallel to lamination, the width of pre-existing micro-fracture initially decreases and leads to crack-healing. Subsequently, the crack surfaces slightly collapse and the micro-fracture width is enlarged. In contrast, imbibition perpendicular to lamination does not generate new micro-fracture. Our results imply that during the flowback process of hydraulic fracturing fluid, the shale permeability parallel to bedding planes likely decreases first then increases, thereby promoting the water uptake.

Conventional reservoir drill-in fluids used for drilling reservoirs in Weizhou Oilfield encounter rheological problems that result in technical problems such as hole-cleaning in openhole horizontal intervals. Hence, novel drill-in fluid was developed by optimizing the additive quantity and particle size distribution. Lab tests showed that novel drill-in fluids boast high low shearing rate viscosity, and provide promising cutting, carrying, and suspension capabilities. Furthermore, the novel drill-in fluids performed well in reservoir protection, with a permeability recovery rate of more than 90%. The novel drill-in fluids also have high inhibition capabilities with a linear expansion rate of mud shale as low as 10%, with a rolling recovery rate of up to 96.48%. Field application results showed no pipe-stuck was encountered during tripping in the horizontal interval when using the novel drill-in fluid. Moreover, by using the novel drill-in fluids, skin factor was reduced from 20.0 to −3.0, and daily oil production was double what was expected. It was concluded that novel drill-in fluids meets the demand of horizontal drilling intervals in Weizhou Oilfield and improves hole-cleaning and reservoir protection in the horizontal well.

Wellbore stability is a key factor affecting safe and efficient drilling. At present, it is difficult to conduct real-time and accurate analysis of wellbore stability in related research. To address the current research shortcomings, this study proposes a real-time analysis model of wellbore stability integrating image recognition and an expert system, which mainly includes caving image segmentation and recognition, and a wellbore stability expert system. The caving image recognition proposes a new dynamic threshold segmentation method based on simple linear iterative clustering superpixel segmentation and visual geometry group 19-layer image classification. After completing the segmentation of the caving image, the geometric features of the caving are calculated, and the multi-source feature fusion GoogleNet model is established by integrating the geometric features with the convolution features extracted by GoogleNet to identify the caving types efficiently. After segmentation and recognition of caving images. The wellbore stability expert system uses the caving features to establish an expert system model to determine the mechanism of wellbore instability and provide reasonable solutions. Finally, the wellbore stability integrating image recognition and an expert system model was applied to a well in field production, accurately determining the mechanism of wellbore instability in real time and effectively solving the corresponding wellbore instability problem based on the measures provided by the model. Document Type: Original article Cited as: Fan, Y., Pang, H., Jin, Y., Meng, H., Lu, Y., Wei, S., Wang, H. Integration of image recognition and expert system for real-time wellbore stability analysis. Advances in Geo-Energy Research, 2025, 15(2): 158-171. https://doi.org/10.46690/ager.2025.02.07