With the tertiary oil recovery in the oilfield, the content of aging oil emulsion with high water content and complex components has become more prevalent, so it is crucial for aging oil to break the emulsification. In this paper, the experimental laws of water content are explored under the conditions of different transducer input powers through the ultrasonic reforming of aging oil, and the microscopic topography, particle size, components, etc. of oil samples before and after the irradiation of ultrasound are characterized through the microscopic analysis, particle size analysis and component analysis and other ways. The results show that the oil samples achieve the effect of demulsification and dehydration in the presence of ultrasonic cavitation effect, with a maximum dehydration rate of 98.24 %, and that the dehydration rate follows an "M-type" trend with the increase of power. The results of microscopic and particle size analyses demonstrate that ultrasonic irradiation destabilizes the oil-water interfacial membrane, and causes droplets of different sizes to collide, agglomerate, and settle. It was also observed that the droplets of the emulsion system are more evenly distributed and the intervals are increased. Furthermore, we hypothesize that ultrasound may be less irreversible in demulsification and dehydration of aging oil.

It is rather significant to reveal the real-time variation of oil sample viscosity during ultrasonic irradiation to research the mechanism of viscosity change. In this paper, we first simulate the acoustic field distribution law in the reaction chamber by using the finite element method and orthogonal experiment method, then measure the viscosity of the oil sample with temperature by vibration type viscometer and get the corresponding function equation by fitting. On this basis, we measure the viscosity of the oil sample with ultrasonic irradiation time and electric power change in real-time and in situ, and finally analyze the mechanism of oil sample viscosity variation by using a temperature recorder and cavitation noise method. The results show that the greatest influence on the acoustic pressure in the reaction chamber is the change of the transducer probe in the height Z direction, followed by the width X direction and the depth Y direction. The viscosity of the oil sample shows an exponential decay with the increase in temperature. With the increase of ultrasonic irradiation time and electric power, the viscosity of the oil sample is gradually reduced. By comparing the effect of heating and ultrasonic irradiation on viscosity, it is found that ultrasonic irradiation not only changes the viscosity through thermal effect but also the cavitation noise analysis and the phenomena observed in the experiment confirm that the cavitation effect and mechanical effect exist all the time.

The reserves of heavy oil are enormous. However, its high viscosity and other characteristics make heavy oil extraction and transportation extremely difficult. Power ultrasonic (US) reforming technology on heavy oil has the advantages of environmental protection and fast results, so it is important to understand the mechanism of ultrasonic reforming. We examine the influence law of the electric power input of the US transducer on the viscosity of heavy oil. Fourier Transform Infrared Spectrometer (FTIR) and Gas Chromatography (GC) are applied to explain the changes in different functional groups, heavy components, and carbon chains before and after US irradiation. The cavitation noise method is also used to study the influences of variance in the intensity of cavitation on the viscosity of heavy oil. The results indicate that the viscosity of heavy oil first decreases, and next increases with an increase in electric power. The functional groups and chromatographic distillation also change in different forms, and with an increase in electric power, the cavitation effect is gradually enhanced. These findings suggest that it is not that the stronger the cavitation, the greater the influence on the viscosity of heavy oil.

Accurate pore pressure estimation in tight sandstone reservoirs is hampered by the limited sensitivity of conventional approaches, which rely on a single acoustic or resistivity log and assume shale undercompaction as the dominant overpressure mechanism. This study develops a hybrid BiLSTM-CNN model that integrates multi-parameter well-log responses to predict pore pressure equivalent density in the Upper Triassic XJH Formation of the northeastern Sichuan Basin, a tight sandstone succession deposited at the end of the Late Triassic. Downhole pressure measurements from five wells and their corresponding logging curves were compiled, yielding 2163 data points after outlier filtering and missing-value interpolation. Grey relational analysis (GRA) ranked six logging parameters—acoustic transit time, bulk density, invaded-zone resistivity, compressional slowness, deep lateral resistivity, and gamma ray—as the most informative model inputs. The network couples a two-layer BiLSTM with 64 hidden units per layer for bidirectional depth-sequence modeling and three parallel one-dimensional convolutional branches with dilation rates of 1, 2, and 3 for multi-scale local feature extraction. The model of test data achieved R² = 0.968, RMSE = 0.0147 g/cm³, and MAE = 0.0116 g/cm³, outperforming four benchmark algorithms (BP, KNN, GBRT, and SVR). Predicted pressure profiles for a verification well reproduced lithologically controlled pressure contrasts between sandstone and mudstone members. Spatial pressure maps for the X2, X4, and X6 intervals, generated by interpolating predictions across multiple wells, show that overpressured zones coincide with greater burial depth and stronger top-seal integrity. These findings demonstrate that coupling depth-directional sequence learning with multi-scale convolutional feature extraction offers a reliable data-driven framework for pore pressure characterization in low-porosity clastic systems.