Hasil untuk "Oils, fats, and waxes"

Romina Hashami, Felipe Maldonado

Financial markets can be highly sensitive to news, investor sentiment, and economic indicators, leading to important asset price fluctuations. In this study we focus on crude oil, due to its crucial role in commodity markets and the global economy. Specifically, we are interested in understanding the directional changes of oil price volatility, and for this purpose we investigate whether news alone -- without incorporating traditional market data -- can effectively predict the direction of oil price movements. Using a decade-long dataset from Eikon (2014-2024), we develop an ensemble learning framework to extract predictive signals from financial news. Our approach leverages diverse sentiment analysis techniques and modern language models, including FastText, FinBERT, Gemini, and LLaMA, to capture market sentiment and textual patterns. We benchmark our model against the Heterogeneous Autoregressive (HAR) model and assess statistical significance using the McNemar test. While most sentiment-based indicators do not consistently outperform HAR, the raw news count emerges as a robust predictor. Among embedding techniques, FastText proves most effective for forecasting directional movements. Furthermore, SHAP-based interpretation at the word level reveals evolving predictive drivers across market regimes: pre-pandemic emphasis on supply-demand and economic terms; early pandemic focus on uncertainty and macroeconomic instability; post-shock attention to long-term recovery indicators; and war-period sensitivity to geopolitical and regional oil market disruptions. These findings highlight the predictive power of news-driven features and the value of explainable NLP in financial forecasting.

Francis Tembo, Federica Bragone, Tor Laneryd et al.

Power transformers are subjected to electrical currents and temperature fluctuations that, if not properly controlled, can lead to major deterioration of their insulation system. Therefore, monitoring the temperature of a power transformer is fundamental to ensure a long-term operational life. Models presented in the IEC 60076-7 and IEEE standards, for example, monitor the temperature by calculating the top-oil and the hot-spot temperatures. However, these models are not very accurate and rely on the power transformers' properties. This paper focuses on finding an alternative method to predict the top-oil temperatures given previous measurements. Given the large quantities of data available, machine learning methods for time series forecasting are analyzed and compared to the real measurements and the corresponding prediction of the IEC standard. The methods tested are Artificial Neural Networks (ANNs), Time-series Dense Encoder (TiDE), and Temporal Convolutional Networks (TCN) using different combinations of historical measurements. Each of these methods outperformed the IEC 60076-7 model and they are extended to estimate the temperature rise over ambient. To enhance prediction reliability, we explore the application of quantile regression to construct prediction intervals for the expected top-oil temperature ranges. The best-performing model successfully estimates conditional quantiles that provide sufficient coverage.

JIE Zhijun, MA Xiaojing, CAI Wenzhe et al.

The tight sandstone gas reservoir in a certain area of Shanxi Province is characterized by low porosity and low permeability. The relationship between pore structure, resistivity and gas and water is complex. The reservoir characteristics pose challenges to the traditional gas layer interpretation and evaluation methods mainly based on resistivity logging. Therefore, it is urgent to seek a gas layer evaluation method that is suitable for such complex reservoirs and well conditions. This paper is based on the small-diameter pulsed neutron saturation logging tool - reservoir evaluation tool (RET), and uses the Fast Neutron Cross Section (FNXS) method to evaluate gas layers.. Based on the feature that FNXS is sensitive to gas but not to non-gas, the FNXS value characterization formula is obtained through Monte Carlo numerical simulation under complex pore structure conditions. The correctness of the FNXS characterization formula is verified in the standard calibration well, and the gas saturation of the reservoir is calculated. The accuracy of this method is verified through field gas testing. Meanwhile, through the data analysis of multiple wells in the block, the FNXS value characterization formula for mudstone correction suitable for this block is established, further improving the accuracy of gas saturation calculation and forming the preliminary gas layer evaluation standard for this block. Practice has proved that the FNXS method based on the RET instrument can quickly identify gas layers under complex formation and well conditions. After slime emendation, the FNXS value characterization is more accurate and the calculation of gas saturation is more precise. This research effectively guides the exploration and evaluation of tight gas in the study block. In - depth research on the FNXS method shows that this method can also be popularized and applied in conventional gas - bearing reservoirs.

ZHU XIANGYU, YU WENQUAN, ZHANG JIANWEI et al.

The deep oil and gas exploration area serves as a crucial position for resource development in Subei Basin . However, challenges including generally poor physical properties of deep reservoirs, insufficient understanding of oil and gas enrichment mechanisms, and ineffective reservoir prediction to meet exploration demands have constrained the expansion of deep oil and gas exploration. To understand the enrichment mechanisms of deep oil and gas, develop key exploration technologies, and indicate future research directions, this paper focuses on the deep layers of Gaoyou and Jinhu Sags, which are rich in oil and gas resources. Firstly, by analyzing the exploration development trends and oil and gas resource potential in oil and gas enrichment Sags such as Gaoyou and Jinhu, along with physical characteristics and main controlling factors of deep reservoirs, it was believed that the deep oil and gas reservoirs in Gaoyou and Jinhu Sags were mainly characterized by low to extra-low porosity and permeability. Secondary pore was the main pore type, while primary pore occurred locally. Overall, as burial depth increased, the proportion of primary pores gradually decreased. Subsequently, based on the relationship between pores and pore throats, deep reservoirs were classified into four types of pore-throat structures: large intergranular pores and wide lamellar throats; small intergranular pores and narrow lamellar throats; intragranular dissolution pores and narrow lamellar throats; and micropores and tubular throats. The physical properties of deep reservoirs were generally poor, with locally developed favorable reservoirs. The factors influencing the physical properties of deep reservoirs were complex. Analysis suggests that sedimentary factors, diagenesis, tectonic activity, oil and gas injection, and abnormal formation pressures all significantly affected the physical properties of deep reservoirs, although the controlling factors and their effects varied across different regions. Secondly, investigations were conducted on the occurrence conditions, main controlling factors, and accumulation models of deep oil and gas. The occurrence conditions of oil and gass suggested that oil and gas migration and accumulation were controlled by the pressure systems and physical properties between source rocks and reservoirs, as well as between different reservoirs. Oil and gas accumulation occurred when migration forces overcame migration resistance. Microscopically, pore-throat structure determined the fluid occurrence state and permeability. Larger throat radii, lower pore-throat radius ratios, and smaller tortuosities led to enhanced pore-throat connectivity and higher reservoir permeability. Macroscopically, pressure increase with oil and gas generation provided the driving force for oil and gas migration and accumulation. The magnitude and direction of source-reservoir pressure difference decided the favorable trends for oil and gas migration and accumulation, controlling their favorable areas. In terms of the main controlling factors for oil and gas enrichment, it was believed that oil and gas accumulation and enrichment in deep reservoirs were jointly controlled by source-reservoir configuration, pressure increase with oil and gas generation, fault-sandstone carrier system, and reservoir physical properties. Three accumulation models for deep oil and gas enrichment were established: stepped accumulation driven by combined abnormal overpressure and buoyancy, accumulation via fault-sandstone carrier system driven by abnormal overpressure, and accumulation of early-stage oil and gas injection followed by later-stage compaction. These models elucidated the enrichment mechanisms of deep oil and gass. Based on the above, to address exploration challenges such as unclear reservoir distribution, undefined enrichment zones, and low identification accuracy of effective reservoirs, three breakthrough technologies were developed: (1) A facies-controlled index method for deep reservoir classification was developed based on “facies-controlled index, porosity-permeability characteristics, pore structures, and diagenetic facies”. Reservoir classification criteria were formulated, categorizing reservoirs into four grades. Effective reservoirs in deep layers were mainly grades Ⅱ and Ⅲ. The distribution of effective reservoirs in the deep layers was evaluated across key stratigraphic intervals, revealing the graded distribution of reservoirs in deep zones of the first and third member of Funing Formation, the third submember in the first member of Dainan Formation in Gaoyou Sag, and the second member of Funing Formation in Jinhu Sag. The favorable areas of effective reservoirs in the deep layers of each stratigraphic system in each Sag were finally determined. (2) Through the analysis of deep oil and gas enrichment mechanisms, and according to the dynamic conditions of oil and gas injection, models for calculating reservoir potential energy, fluid potential, and source-reservoir pressure differences were established. Subsequently, a model for calculating the reservoir injection potential energy index were established based on the above models. Finally, the obtained reservoir injection potential energy index was used to assess the probability of oil and gas accumulation, providing technical support for the selection of favorable oil and gas accumulation zones in deep layers. (3) Subaqueous distributary channels and beach-bar sand bodies were effective reservoirs for deep oil and gass. To address the challenge of effective reservoir prediction in thin sandstone-mudstone interbeds within favorable oil and gas accumulation zones in selected deep layers, an integrated technical suite for effective reservoir prediction was developed. This technique, tailored to different sand body types such as channels and beach bars, integrated pre-stack and post-stack multi-attribute analysis. It leveraged geological, petrophysical, seismic, statistical, and other disciplinary theories to provide a comprehensive approach to reservoir prediction. Based on the distinction between sandstone and mudstone, this suite included six techniques for reservoir prediction: effective reservoir modeling based on petrophysical analysis, post-stack multi-parameter inversion constraint method, pre-stack and post-stack joint inversion method, seismic attribute threshold analysis method, seismic multi-attribute neural network prediction method, and SP curve reconstruction for acoustic curve. These techniques collectively improved the prediction accuracy of effective reservoirs in deep layers. These research findings provide theoretical guidance and technical support for the expansion of deep oil and gas exploration. Significant exploration progress has been made in deep layers such as slope zones, fault zones, and deep sag zones, enabling the expansion of deep oil and gas exploration. In the future, the research directions for addressing challenges in deep oil and gas exploration are clarified, which are continuing to consolidate and expand deep exploration to support the increase in oilfield reserves and production.

Wanting Zhang, Wei Du, Guo Yu et al.

With the scaling up of crude oil scheduling in modern refineries, large-scale crude oil scheduling problems (LSCOSPs) emerge with thousands of binary variables and non-linear constraints, which are challenging to be optimized by traditional optimization methods. To solve LSCOSPs, we take the practical crude oil scheduling from a marine-access refinery as an example and start with modeling LSCOSPs from crude unloading, transportation, crude distillation unit processing, and inventory management of intermediate products. On the basis of the proposed model, a dual-stage evolutionary algorithm driven by heuristic rules (denoted by DSEA/HR) is developed, where the dual-stage search mechanism consists of global search and local refinement. In the global search stage, we devise several heuristic rules based on the empirical operating knowledge to generate a well-performing initial population and accelerate convergence in the mixed variables space. In the local refinement stage, a repair strategy is proposed to move the infeasible solutions towards feasible regions by further optimizing the local continuous variables. During the whole evolutionary process, the proposed dual-stage framework plays a crucial role in balancing exploration and exploitation. Experimental results have shown that DSEA/HR outperforms the state-of-the-art and widely-used mathematical programming methods and metaheuristic algorithms on LSCOSP instances within a reasonable time.

Alberto Silvio Chiappa, Briti Gangopadhyay, Zhao Wang et al.

Online advertising has become one of the most successful business models of the internet era. Impression opportunities are typically allocated through real-time auctions, where advertisers bid to secure advertisement slots. Deciding the best bid for an impression opportunity is challenging, due to the stochastic nature of user behavior and the variability of advertisement traffic over time. In this work, we propose a framework for training auto-bidding agents in multi-slot second-price auctions to maximize acquisitions (e.g., clicks, conversions) while adhering to budget and cost-per-acquisition (CPA) constraints. We exploit the insight that, after an advertisement campaign concludes, determining the optimal bids for each impression opportunity can be framed as a multiple-choice knapsack problem (MCKP) with a nonlinear objective. We propose an "oracle" algorithm that identifies a near-optimal combination of impression opportunities and advertisement slots, considering both past and future advertisement traffic data. This oracle solution serves as a training target for a student network which bids having access only to real-time information, a method we term Oracle Imitation Learning (OIL). Through numerical experiments, we demonstrate that OIL achieves superior performance compared to both online and offline reinforcement learning algorithms, offering improved sample efficiency. Notably, OIL shifts the complexity of training auto-bidding agents from crafting sophisticated learning algorithms to solving a nonlinear constrained optimization problem efficiently.

Owais Ishtiaq Siddiqui, Nouhaila Innan, Alberto Marchisio et al.

Quantum Machine Learning (QML) has shown promise in diverse applications such as environmental monitoring, healthcare diagnostics, and financial modeling. However, its practical implementation faces challenges, including limited quantum hardware and the complexity of integrating quantum algorithms with classical systems. One critical challenge is handling imbalanced datasets, where rare events are often misclassified due to skewed data distributions. Quantum Bayesian Networks (QBNs) address this issue by enhancing feature extraction and improving the classification of rare events such as oil spills. This paper introduces a Bayesian approach utilizing QBNs to classify satellite-derived imbalanced datasets, distinguishing ``oil-spill'' from ``non-spill'' regions. QBNs leverage probabilistic reasoning and quantum state preparation to integrate quantum enhancements into classical machine learning architectures. Our approach achieves a 0.99 AUC score, demonstrating its efficacy in anomaly detection and advancing precise environmental monitoring and management. While integration enhances classification performance, dataset-specific challenges require further optimization.

Seyed Reza ASADOLAHPOUR, Zeyun JIANG, Helen LEWIS et al.

In order to predict phase distributions within complex pore structures during two-phase capillary-dominated drainage, we select subsamples from computerized tomography (CT) images of rocks and simulated porous media, and develop a pore morphology-based simulator (PMS) to create a diverse dataset of phase distributions. With pixel size, interfacial tension, contact angle, and pressure as input parameters, convolutional neural network (CNN), recurrent neural network (RNN) and vision transformer (ViT) are transformed, trained and evaluated to select the optimal model for predicting phase distribution. It is found that commonly used CNN and RNN have deficiencies in capturing phase connectivity. Subsequently, we develop a higher-dimensional vision transformer (HD-ViT) that drains pores solely based on their size, regardless of their spatial location, with phase connectivity enforced as a post-processing step. This approach enables inference for images of varying sizes and resolutions with inlet-outlet setup at any coordinate directions. We demonstrate that HD-ViT maintains its effectiveness, accuracy and speed advantage on larger sandstone and carbonate images, compared with the microfluidic-based displacement experiment. In the end, we train and validate a 3D version of the model.

Li Jiayi, Liu Xiuquan, Xu Liangbin et al.

The traditional evaluation on wave induced fatigue of subsea wellhead does not consider the changes in the composition of subsea wellhead structure at different drilling stages,resulting in limited accuracy in wave induced fatigue evaluation of subsea wellhead. A fine evaluation method for wave induced fatigue of subsea wellhead in full drilling process based on global-local interaction analysis was proposed. A local fine model for subsea wellhead with complex structure and a global model for platform-riser-subsea wellhead-conductor coupling system in the full drilling process were built. The interaction mechanism between global model and local model was studied. The transitive relation between global model and local stress was constructed to finely evaluate the wave induced fatigue damage of subsea wellhead in full drilling process. The results show that the changes in the composition of subsea wellhead structure have almost no effect on the wave induced fatigue of the riser system and the conductor far away from the mud line in full drilling process,but have a significant impact on the wave induced fatigue of local part of subsea wellhead and the conductor near the mud line. At the second stage of drilling,the wave induced fatigue damage to the subsea wellhead is the most severe,and the bottom of the subsea wellhead is always at the fatigue limit position. The conclusions are helpful in judging the fatigue of subsea wellhead during drilling and ensuring the safety of drilling operations.

Mahdi Hosseini, Seyed Hayan Zaheri, Ali Roosta

Abstract During the development of a field, many fluid samples are taken from wells. Selecting a robust fluid sample as the reservoir representative helps to have a better field characterization, reliable reservoir simulation, valid production forecast, efficient well placement and finally achieving optimized ultimate recovery. First, this paper aims to detect and separate the samples that have been collected under poor conditions or analyzed in a non-standard way. Moreover, it introduces a novel ranking method to score the samples based on the amount of coordination with other fluid samples in the region. The dataset includes 136 fluid samples from five reservoirs in Iranian fields, each of them consisting of 21 key parameters. Five acknowledged machine learning based anomaly detection techniques are implemented to compare fluid samples and detect those whose results deviate from others, indicating non-standard samples. To ensure the proper detection of outlier data, the results are compared with the traditional validation method of gas-oil ratio estimation. All five outlier detection methods demonstrate acceptable performance with average accuracy of 79% compared to traditional validation. Furthermore, the fluid samples with the highest scores in scoring-based algorithms are introduced as the best reservoir’s representative fluid. Finally, fuzzy logic is used to obtain a final score for each sample, taking the results of the six methods as input and ranking the samples based on their output score. The study confirms the robustness of the novel approach for fluid validation using outlier detection techniques and the value of machine learning and fuzzy logic for sample ranking, excelling in considering all critical fluid parameters simultaneously over traditional methods.

Himmet Kaplan, Ralf-Peter Mundani, Heiko Rölke et al.

Predicting market movements based on the sentiment of news media has a long tradition in data analysis. With advances in natural language processing, transformer architectures have emerged that enable contextually aware sentiment classification. Nevertheless, current methods built for the general financial market such as FinBERT cannot distinguish asset-specific value-driving factors. This paper addresses this shortcoming by presenting a method that identifies and classifies events that impact supply and demand in the crude oil markets within a large corpus of relevant news headlines. We then introduce CrudeBERT, a new sentiment analysis model that draws upon these events to contextualize and fine-tune FinBERT, thereby yielding improved sentiment classifications for headlines related to the crude oil futures market. An extensive evaluation demonstrates that CrudeBERT outperforms proprietary and open-source solutions in the domain of crude oil.

Farshid Keivanian, Raymond Chiong, Zongwen Fan

Predicting body fat can provide medical practitioners and users with essential information for preventing and diagnosing heart diseases. Hybrid machine learning models offer better performance than simple regression analysis methods by selecting relevant body measurements and capturing complex nonlinear relationships among selected features in modelling body fat prediction problems. There are, however, some disadvantages to them. Current machine learning. Modelling body fat prediction as a combinatorial single- and multi-objective optimisation problem often gets stuck in local optima. When multiple feature subsets produce similar or close predictions, avoiding local optima becomes more complex. Evolutionary feature selection has been used to solve several machine-learning-based optimisation problems. A fuzzy set theory determines appropriate levels of exploration and exploitation while managing parameterisation and computational costs. A weighted-sum body fat prediction approach was explored using evolutionary feature selection, fuzzy set theory, and machine learning algorithms, integrating contradictory metrics into a single composite goal optimised by fuzzy adaptive evolutionary feature selection. Hybrid fuzzy adaptive global learning local search universal diversity-based feature selection is applied to this single-objective feature selection-machine learning framework (FAGLSUD-based FS-ML). While using fewer features, this model achieved a more accurate and stable estimate of body fat percentage than other hybrid and state-of-the-art machine learning models. A multi-objective FAGLSUD-based FS-MLP is also proposed to analyse accuracy, stability, and dimensionality conflicts simultaneously. To make informed decisions about fat deposits in the most vital body parts and blood lipid levels, medical practitioners and users can use a well-distributed Pareto set of trade-off solutions.

Takaaki Matsunaga, Atsushi Kono, Hidetoshi Matsuo et al.

Rationale and Objectives: Pericardial fat (PF), the thoracic visceral fat surrounding the heart, promotes the development of coronary artery disease by inducing inflammation of the coronary arteries. For evaluating PF, this study aimed to generate pericardial fat count images (PFCIs) from chest radiographs (CXRs) using a dedicated deep-learning model. Materials and Methods: The data of 269 consecutive patients who underwent coronary computed tomography (CT) were reviewed. Patients with metal implants, pleural effusion, history of thoracic surgery, or that of malignancy were excluded. Thus, the data of 191 patients were used. PFCIs were generated from the projection of three-dimensional CT images, where fat accumulation was represented by a high pixel value. Three different deep-learning models, including CycleGAN, were combined in the proposed method to generate PFCIs from CXRs. A single CycleGAN-based model was used to generate PFCIs from CXRs for comparison with the proposed method. To evaluate the image quality of the generated PFCIs, structural similarity index measure (SSIM), mean squared error (MSE), and mean absolute error (MAE) of (i) the PFCI generated using the proposed method and (ii) the PFCI generated using the single model were compared. Results: The mean SSIM, MSE, and MAE were as follows: 0.856, 0.0128, and 0.0357, respectively, for the proposed model; and 0.762, 0.0198, and 0.0504, respectively, for the single CycleGAN-based model. Conclusion: PFCIs generated from CXRs with the proposed model showed better performance than those with the single model. PFCI evaluation without CT may be possible with the proposed method.

M. Fasano, Y. Li, J. A. Diez et al.

We present a theoretical study, supported by simulations and experiments, on the spreading of a silicone oil drop under MHz-frequency surface acoustic wave (SAW) excitation in the underlying solid substrate. Our time-dependent theoretical model uses the long wave approach and considers interactions between fluid dynamics and acoustic driving. While similar methods have analyzed micron-scale oil and water film dynamics under SAW excitation, acoustic forcing was linked to boundary layer flow, specifically Schlichting and Rayleigh streaming, and acoustic radiation pressure. For the macroscopic drops in this study, acoustic forcing arises from Reynolds stress variations in the liquid due to changes in the intensity of the acoustic field leaking from the SAW beneath the drop and the viscous dissipation of the leaked wave. Contributions from Schlichting and Rayleigh streaming are negligible in this case. Both experiments and simulations show that after an initial phase where the oil drop deforms to accommodate acoustic stress, it accelerates, achieving nearly constant speed over time, leaving a thin wetting layer. Our model indicates that the steady speed of the drop results from the quasi-steady shape of its body. The drop speed depends on drop size and SAW intensity. Its steady shape and speed are further clarified by a simplified traveling wave-type model that highlights various physical effects. Although the agreement between experiment and theory on drop speed is qualitative, the results' trend regarding SAW amplitude variations suggests that the model realistically incorporates the primary physical effects driving drop dynamics.

Harald G Svendsen, Til Kristian Vrana, Andrzej Holdyk et al.

This article introduces and describes the integrated energy system of a the Low Emission Oil&Gas Open (LEOGO) reference platform. It is a hypothetical case meant to represent a typical oil&gas installation in the North Sea. The aim of this detailed specification is to serve as an open reference case where all information about it can be publicly shared, facilitating benchmarking and collaboration. The relevance of this reference case of an off-grid energy system is not limited to the oil&gas industry, since it can also been seen as a special kind of electrical micro grid. The remote offshore location makes it especially relevant for studying offshore wind power and ocean energy sources like wave power. The specification has an emphasis on the energy system and electrical configuration, but includes also a basic description of oil field and processing system. The intention is that it will serve as a basis for energy system studies and relating power system stability analyses regarding the integration of renewable energy sources. This allows for comparisons of a base case with different design modifications, new operational planning methods, power management strategies and control concepts. Examples of possible modifications are the replacement of gas turbines by wind turbines, addition of energy storage systems, a more variable operation of loads, etc. The last part of the article demonstrates the behaviour of the reference platform implemented in two software tools. One for operational planning and one for dynamic power system analyses.

LI Hongwei, YUAN Jian, ZHAO Zhichuan et al.

The J<i>S</i>₂² gas reservoir in the Xinchang Gas Field is the microfacies of distributary channel deposit in the delta front subfacies. The mudstone interlayer developed in some sandstone layers form the channel sediments twice. For some gas wells with double developed sand layers, the perforation and fracturing are carried out only in one of the two layers, while the rest may be blocked by mudstone interlayer, resulting in its untapped situation. However, the understanding of the distribution rule of the mudstone interlayer is unclear, and the sealing performance of interlayers hasn't been verified by precedent, limiting the development of the remaining gas in this reservoir. By the establishment of the logging curve identification standards of the interlayer, the interlayer of every single well is identified and divided, and the development scale and plane distribution rule of the interlayer are studied. And then, the old wells are used to explore the vertical sealing performance of the mudstone interlayer inside the channel sandstone. The study results show that the mudstone interlayer, with the thickness of 1~15 meters, is mainly distributed in the east of the J<i>S</i>₂² gas reservoir, and has the characteristic of one thin-line area laying between two thick areas along the distribution direction. In the application of potential tapping of Well-A1, the production obviously increase after the perforation and sand-fracture, firstly verifying that the mudstone interlayer with the thickness of 10 meters in A1 well area has better vertical sealing performance. This achievement will provide new ideas and practical basis for the development of remaining gas in the J<i>S</i>₂² gas reservoir, and is of great significance for improving the recovery rate of the entire gas reservoir.

Afanas'eva M.A., Chzhan Ee

The deltas developed widely in several faulted basins in China. As a kind of important oil and gas reservoir, it is very necessary to make clear the internal architecture for prediction of the residual oil distribution in the late period of oilfield development．Therefore taking the 5th oil productive level of Kongdian Formation in the faulted block 195 of Y oil field as an example the reservoir architecture of delta front was characterized quantitatively based on core data well logs and production data．The main reservoir architecture elements off an delta front consists of distributary channel, estuary sandbar, sheet sand and inter channel．The division scheme was established for the division of reservoir architecture of delta front into different levels and the markers was defined for the identification of distributary channel estuary sandbar and inner accretion body in estuary sandbar．Taking single sandbody as a unit data being acquired from field outcrop defined as delta in the Xiguayuan Formation of Luanping Basin were matched to derive a formula for quantitative characterization of distributary channel and estuary sandbar, calculation of the dip of interbed innerestuary sandbar and prediction of the development of inner accretion body．The residual oil controlled by a single genetic sand body distributes at the top of the margin of sandbars and channels and the distribution of residual oil controlled by the interlayer should be analyzed according to the specific rhythm of the sandbar.

Bingyang Chena, Xingjie Zenga, Weishan Zhang

Cross-block oil-water layer(OWL) identification is essential for petroleum development. Traditional methods are greatly affected by subjective factors due to depending mainly on the human experience. AI-based methods have promoted the development of OWL identification. However, because of the significant geological differences across blocks and the severe long-tailed distribution(class imbalanced), the identification effects of existing artificial intelligence(AI) models are limited. In this paper, we address this limitation by proposing a dynamic fusion-based federated learning(FL) for OWL identification. To overcome geological differences, we propose a dynamic weighted strategy to fuse models and train a general OWL identification model. In addition, an F1 score-based re-weighting scheme is designed and a novel loss function is derived theoretically to solve the data long-tailed problem. Further, a geological knowledge-based mask-attention mechanism is proposed to enhance model feature extraction. To our best knowledge, this is the first work to identify OWL using FL. We evaluate the proposed approach with an actual well logging dataset from the oil field and a public 3W dataset. Experimental results demonstrate that our approach significantly out-performs other AI methods.

Qiang Jie, Qi Yuekui, Liu Xueguang et al.

At present, the casing failure injection wells in Dagang Oilfield account for 9.2% of the total number of oil and water wells in the oilfield, which affects the stable production and production increase of the oilfield. In view of this, the technological plan of using expansion pipe patch technology to repair the casing failure well was established. After having briefly introduced the principle of expansion pipe patch technology, the structural composition of patch tool string, the operation technology and the technological characteristics, this article carried out mechanical property test on the expansion pipe patch tubular goods, optimized high strength and low cost tubular goods 20G, used the multi-stage force-increasing cold drawing expansion forming process of &#248;139.7 mm casing to form large drift diameter expansion pipe patch technology, and subsequently carried out expansion pipe patch laboratory test. The test results show that the expansion pressure of the expansion pipe is 14～18 MPa, and the expansion rate of it is greater than 8.94%; the expansion pipe and the casing can withstand 500 kN tension without relative movement; the anchoring seal between the tubular goods and the casing is reliable, and the large drift diameter of the patch section is realized. This technology has been successfully applied in Well Jia47-7 of Dagang Oilfield, and the expansion pipe patch achieves the expected effect of plugging the leakage point of the pipe, which provides technical support and reference for the repair of casing failure injection wells in the oilfield.

Lichun KUANG, He LIU, Yili REN et al.

Aiming at the actual demands of petroleum exploration and development, this paper describes the research progress and application of artificial intelligence (AI) in petroleum exploration and development, and discusses the applications and development directions of AI in the future. Machine learning has been preliminarily applied in lithology identification, logging curve reconstruction, reservoir parameter estimation, and other logging processing and interpretation, exhibiting great potential. Computer vision is effective in picking of seismic first breaks, fault identification, and other seismic processing and interpretation. Deep learning and optimization technology have been applied to reservoir engineering, and realized the real-time optimization of waterflooding development and prediction of oil and gas production. The application of data mining in drilling, completion, and surface facility engineering etc. has resulted in intelligent equipment and integrated software. The potential development directions of artificial intelligence in petroleum exploration and development are intelligent production equipment, automatic processing and interpretation, and professional software platform. The highlights of development will be digital basins, fast intelligent imaging logging tools, intelligent seismic nodal acquisition systems, intelligent rotary-steering drilling, intelligent fracturing technology and equipment, real-time monitoring and control of zonal injection and production.