Search Results (13)

In China, a majority of the proven crude oil reserves are found in clastic rock reservoirs, which typically exhibit low natural energy levels. Water injection has become the most widely adopted technique for maintaining reservoir pressure and enhancing oil recovery in such formations. However, conventional water injection strategies heavily rely on empirical knowledge, often failing to accurately characterize the dynamic inter-well connectivity between injection and production wells. This limitation hinders the effective management of fluid injection and production processes. To address this challenge, we propose an intelligent optimization method for water allocation in high-water cut, low-permeability reservoirs. Our approach employs a Bidirectional Long Short-Term Memory (BiLSTM) neural network to learn the complex patterns from historical injection data in a data-driven manner. Furthermore, we design a well distance and time joint attention mechanism, which is integrated after the dual BiLSTM layers to enhance the model’s ability to capture the critical dynamic relationships among wells. This mechanism decouples temporal pattern recognition and the spatial physical constraints, laying the foundation for interpretable injection strategy optimization. We name this architecture “AttBiLSTM”, which is designed for optimizing injection strategies for individual layers in separate-layer water injection wells (The layer refers to the basic geological unit or flow unit within a vertically heterogeneous reservoir that is delineated and requires independent water injection regulation). Using field data from the Xinjiang Oilfield, we validate the proposed method and compare its performance against traditional water injection schemes and mainstream data-driven models. The experimental results demonstrate that the AttBiLSTM model effectively establishes a nonlinear mapping between the injection volumes and oil production rates, showing strong performance in both production prediction and injection optimization. An independent numerical reservoir simulation verification confirms that the optimized scheme increases well group oil production by over 3.6%, with no premature water breakthrough risk in a 5-year development cycle. This study provides a novel and practical technical framework for efficiently developing low-porosity, low-permeability, and highly heterogeneous reservoirs. Full article

Against the deep integration of digital transformation and AI, cross-institutional collaborative modeling hinges on efficient data circulation, yet data silos and privacy regulations hinder traditional centralized training. Federated Learning (FL) keeps data local but faces issues like weak centralized trust, inadequate privacy protection, and poor robustness in edge networks. Existing improvements, including via differential privacy (DP) and blockchain, among others, still suffer from centralized budget allocation, low consensus efficiency, or single-point-of-failure addressing, failing to jointly optimize trust, performance, and privacy. The limitations are exacerbated in high-frequency, resource-constrained edge environments. To tackle these challenges, this paper proposes BE-DPFL, a blockchain-enhanced differentially private FL framework that integrates on-chain trusted supervision and off-chain efficient training. It builds a lightweight blockchain trust layer with FL-PBFT consensus and smart contracts, introduces Random Projection–ADMM optimization, and designs a multi-objective adaptive gradient clipping/noise injection strategy. Experiments on CIFAR-10 and ChestX-ray14 demonstrate that BE-DPFL outperforms mainstream methods in consensus efficiency, communication overhead, privacy-accuracy balance, and robustness. It reduces communication costs by over 97%, achieves 100% privacy compliance, and maintains stable performance even under high disturbances. Ablation studies confirm the significant contributions of core components. Full article

Cross-site scripting (XSS) attacks are among the threats facing web security, resulting from the diversity and complexity of HTML formats. Research has shown that some text processing-based methods are limited in their ability to detect this type of attack. This article proposes an approach aimed at improving the detection of this type of attack, taking into account the limitations of certain techniques. It combines the effectiveness of deep learning represented by convolutional neural networks (CNN) and the accuracy of classification methods represented by support vector machines (SVM). It takes advantage of the ability of CNNs to effectively detect complex visual patterns in the face of injection variations and the SVM’s powerful classification capability, as XSS attacks often use obfuscation or encryption techniques that are difficult to be detected with textual methods alone. This work relies on a dataset that focuses specifically on XSS attacks, which is available on Kaggle and contains 13,686 sentences in script form, including benign and malicious cases associated with these attacks. Benign data represents 6313 cases, while malicious data represents 7373 cases. The model was trained on 80% of this data, while the remaining 20% was allocated for test. Computer vision techniques were used to analyze the visual patterns in the images and extract distinctive features, moving from a textual representation to a visual one where each character is converted into its ASCII encoding, then into grayscale pixels. In order to visually distinguish the characteristics of normal and malicious code strings and the differences in their visual representation, a CNN model was used in the analysis. The convolution and subsampling (pooling) layers extract significant patterns at different levels of abstraction, while the final output is converted into a feature vector that can be exploited by a classification algorithm such as an Optimized SVM. The experimental results showed excellent performance for the model, with an accuracy of (99.7%), and this model is capable of generalizing effectively without the risk of overfitting or loss of performance. This significantly enhances the security of web applications by providing robust protection against complex XSS threats. Full article

The separate-layer gas injection technology is a key means to improve the effect of refined gas injection development. Currently, the measurement and adjustment of separate injection wells primarily rely on manual experience and automatic measurement via instrument traversal, resulting in a long duration, low efficiency, and low qualification rate for injection allocation across multi-layer intervals. Given the different CO₂-containing natural gas injection rates across different intervals, this paper establishes a coupled flow model of a separate-layer gas injection wellbore–gas distributor–formation based on the energy and mass conservation equations for wellbore pipe flow, and develops a solution method for determining gas nozzle sizes across multi-layer intervals. Based on the maximum allowable gas nozzle size, an optimization method for multi-layer collaborative allocation of separate injection wells is established, with minimum wellhead injection pressure and layered injection allocation as the optimization objectives, and the opening of gas distributors for each layer as the optimization variable. Taking Well XXX as an example, the optimization process of allocation schemes under different gas allocation requirements is simulated. The research shows that the model and method proposed in this paper have high calculation accuracy, and the formulated allocation schemes have strong adaptability and minor injection allocation errors, providing a scientific decision-making method for formulating refined allocation schemes for separate-layer gas injection wells, with significant theoretical and practical value for promoting the refined development of oilfields. Full article

To address prominent challenges in developing high water cut oilfields—such as significant variations in sandstone water absorption capacity and uneven reservoir mobilization—this paper proposes a dynamic layered water injection method centered on seepage resistance as the core regulatory indicator. Through theoretical derivation, quantitative relationships are established between seepage resistance, liquid absorption ratio, and injection allocation. Combined with numerical simulation analysis, this forms a refined water injection control strategy that dynamically adjusts according to changes in oilfield water cut. Research findings demonstrate that this method effectively improves fluid absorption profiles in heterogeneous reservoirs, promotes balanced displacement across distinct lithologic zones, and thereby suppresses water cut increase rates and production decline. Taking Block D as an example, maintaining inter-zone seepage resistance step difference within the 3–5 range yields optimal development outcomes. This study provides significant reference value and practical insights for the dynamic development of oilfields in high water cut phases. Full article

Reservoir heterogeneity, fluid property variations, and permeability contrasts across different geological layers result in significant disparities in water absorption capacities during oilfield development, often leading to premature water breakthrough, uneven sweep efficiency, and suboptimal waterflooding outcomes. The accurate determination of layer-specific water injection volumes is critical to addressing these challenges. This study focuses on a study area in China, employing comprehensive on-site investigations to evaluate the current state of layered water injection practices. The injection allocation strategy was optimized using a hybrid approach combining the splitting coefficient method and grey correlation analysis. Key challenges identified in the study area include severe reservoir heterogeneity, poor injection–production correspondence, rapid water cut escalation, and low recovery rates. Seven dominant influencing factors—the sedimentary microfacies coefficient, effective thickness, stimulation factor, well spacing, permeability, connectivity, and permeability range coefficient—were identified through grey correlation analysis. Field application of the proposed method across fourteen wells demonstrated significant improvements: a monthly oil production increase of 40 tons, a water production reduction of 399.24 m³/month, and a 2.45% decline in the water cut. The obtained results substantiate the method’s capability in resolving interlayer conflicts, optimizing oil recovery performance, and effectively controlling water channeling problems. Full article

In the data-driven healthcare sector, balancing privacy protection and model performance is critical. This paper enhances accuracy and reliability in survival analysis by integrating differential privacy, deep learning, and the Cox proportional hazards model within a federated learning framework. Traditionally, differential privacy’s noise injection often degrades model performance. To address this, we propose two adaptive privacy budget allocation strategies considering weight changes across neural network layers. The first, LS-ADP, utilizes layer sensitivity to assess the influence of individual layer weights on model performance and develops an adaptive differential privacy algorithm. The second, ROW-DP, comprehensively assesses weight variations and absolute values to propose a random one-layer weighted differential privacy algorithm. These algorithms provide differentiated privacy protection for various weights, mitigating privacy leakage while ensuring model performance. Experimental results on simulated and clinical datasets demonstrate improved predictive performance and robust privacy protection. Full article

Electric Vehicle (EV) load forecasting is critical for optimizing resource allocation and ensuring the stability of modern energy systems. However, traditional machine learning models, predominantly based on Multi-Layer Perceptrons (MLPs), encounter substantial challenges in modeling the complex, nonlinear, and dynamic patterns inherent in EV charging data, often leading to overfitting and high computational costs. To overcome these limitations, this study introduces KAN–CNN, a novel hybrid architecture that integrates Kolmogorov–Arnold Networks (KANs) into traditional machine learning frameworks, specifically Convolutional Neural Networks (CNNs). By combining the spatial feature extraction strength of CNNs with the adaptive nonlinearity of KAN, KAN–CNN achieves superior feature representation and modeling flexibility. The key innovations include bottleneck KAN convolutional layers for reducing parameter complexity, Self-Attention Kolmogorov–Arnold Network with Global Nonlinearity (Self-KAGN) Attention to enhance global dependency modeling, and Focal KAGN Modulation for dynamic feature refinement. Furthermore, regularization techniques such as L1/L2 penalties, dropout, and Gaussian noise injection are utilized to enhance the model’s robustness and generalization capability. When applied to EV load forecasting, KAN–CNN demonstrates prediction accuracy comparable to state-of-the-art methods while significantly reducing computational overhead and simplifying parameter tuning. This work bridges the gap between theoretical innovations and practical applications, offering a robust and efficient solution for dynamic energy system challenges. Full article

Due to the advantages of fewer energy conversion stages and a simple structure, direct current (DC) microgrids are being increasingly studied and applied. To minimize distribution loss in DC microgrids, a systematic optimal control framework is proposed in this paper. By considering conduction loss, switching loss, reverse recovery loss, and ohmic loss, the general loss model of a DC microgrid is formulated as a multi-variable convex function. To solve the objective function, a top-layer distributed integral convex optimization algorithm (DICOA) is designed to optimize the current-sharing coefficients by exchanging the gradients of loss functions. Then, the injection currents of distributed energy resources (DERs) are allocated by the distributed adaptive control in the secondary control layer and local voltage–current control in the primary layer. Based on the DICOA, a three-layer control strategy is constructed to achieve loss minimization. By adopting a peer-to-peer data-exchange strategy, the robustness and scalability of the proposed systematic control are enhanced. Finally, the proposed distribution current dispatch control is implemented and verified by simulations and experimental results under different operating scenarios, including power limitation, communication failure, and plug-in-and-out of DERs. Full article

During the water injection development process of highly deviated wells in low-permeability reservoirs, the water flooding distance between different layers of the same oil and water well is different due to the deviation of the well. In addition, the heterogeneity of low-permeability reservoirs is strong, and the water absorption capacity between layers is very different. This results in poor effectiveness of commonly used layered injection methods. Some highly deviated wells have premature water breakthroughs after layered water injection, which affects the development effect of the water flooding reservoirs. Therefore, based on the analysis and research of the existing layered injection allocation method and sand body connectivity evaluation method, considering the influence of sand body connectivity, the real displacement distance of highly deviated wells, reservoir physical properties, and other factors, a new methodology for determination of layered injection allocation in highly deviated wells drilled in low-permeability reservoirs is proposed. In this method, the vertical superposition and lateral contact relationship of a single sand body are determined using three methods: sand body configuration identification, seepage unit identification, and single sand body boundary identification. The connectivity coefficient, transition coefficient, and connectivity degree coefficient are introduced to quantitatively evaluate the connectivity of sand bodies and judge the connectivity relationship between single sand bodies. The correlation formula is obtained using the linear regression of the fracture length and ground fluid volume, and the real displacement distance of each layer in highly deviated wells is obtained. The calculation formula of the layered injection allocation is established by analyzing the important factors affecting the layered injection allocation, and a reasonable layered injection allocation is obtained. The calculation parameters of this method are fully considered, the required parameters are easy to obtain, and the practicability is strong. It can provide a method reference for the policy adjustment of layered water injection technology in similar water injection development reservoirs. Full article

Dye-sensitized solar cells (DSSCs) are a very promising solution as remote sustainable low power sources for portable electronics and Internet of Things (IoT) applications due to their room-temperature and low-cost fabrication, as well as their high efficiency under artificial light. In addition, new achievements in developing semitransparent devices are driving interest in their implementation in the building sector. However, the main obstacle towards the large-scale exploitation of DSSCs mainly concerns their limited long-term stability triggered by the use of liquid electrolytes. Moreover, the device processing generally involves using a thick adhesive separator layer and vacuum filling or injection of the liquid polymer electrolyte between the two electrodes, a method that is difficult to scale up. This review summarizes the advances made in the design of alternative (quasi-)solid polymer electrolytes, with a focus on polysiloxane-based poly(ionic liquid)s. Their behavior in full DSSCs is presented and compared in terms of power generation maximization, advantages and shortcomings of the different device assembly strategies, as well as polymer electrolyte-related processing limitations. Finally, a fair part of the manuscript is allocated to the assessment of liquid and gel polymer electrolyte printability, particularly focusing on polysiloxane-based electrolytes. Spray, blade (slot-dye), screen and inkjet printing technologies are envisaged considering the polymer electrolyte thermophysical and rheological properties, as well as DSSC processing and operating conditions. Full article

Groundwater is the main source of water for drinking, household use, and irrigation in Kabul; however, the water table is dropping due to the excessive extraction over the past two decades. The groundwater restoration criteria selection mainly depends on the techniques used to recharge the aquifer. The design of infiltration basins, for example, requires different technical criteria than the installation of infiltration wells. The different set of parameters is relevant to water being infiltrated at the surface in comparison with water being injected into the aquifers. Restoration of the groundwater resources are complicated and expensive tasks. An inexpensive preliminary investigation of the potential recharge areas, especially in developing countries such as Afghanistan with its complex Upper Indus River Basin, can be reasonably explored. The present research aims to identify the potential recharge sites through employing GIS and Analytical Hierarchy Process (AHP) and combining remote sensing information with in situ and geospatial data obtained from related organizations in Afghanistan. These data sets were employed to document nine thematic layers which include slope, drainage density, rainfall, distance to fault, distance to river channel, lithology, and ground water table, land cover, and soil texture. All of the thematic layers were allocated and ranked, based on previous studies, and field surveys and extensive questionnaire surveys carried out with Afghan experts. Based on the collected and processed data output, the groundwater recharge values were determined. These recharge values were grouped into four classes assessing the suitability for recharge as very high (100%), high (63%), moderate (26%), and low (10%). The relative importance of the various geospatial layers was identified and shows that slope (19.2%) is the most important, and faults (3.8%) the least important. The selection of climatic characteristics and geological characteristics as the most important criteria in the artificial recharge of the aquifer are investigated in many regions with good access to data and opportunities for validation and verifications. However, in regions with limited data due to the complexities in collecting data in Afghanistan, proper researching with sufficient data is a challenge. The novelty of this research is the cross-disciplinary approach with incorporation of a compiled set of input data with the set of various criteria (nine criteria based on which layers are formed, including slope, drainage density, rainfall, distance to fault, distance to river channel, lithology, ground water table, land cover, and soil texture) and experts’ questionnaires. The AHP methodology expanded with the cross-disciplinary approach by adding the local experts´ questionnaires survey can be very handy in areas with limited access to data, to provide the preliminary investigations, and reduce expenses on the localized expensive and often dangerous field works. Full article

With the gradual declining of oil increment performance of CO₂ huff-and-puff wells, the overall oil exchange rate shows a downward tendency. In this regard, CO₂ synergistic huff-and-puff technologies have been proposed to maintain the excellent effect and extend the technical life of such wells. However, there is no specific research on the mechanism and synergistic mode of CO₂ huff and puff in horizontal wells. This study aims to establish the synergistic mode and determine the adaptability and acting mechanism of CO₂ synergistic huff and puff. Three synergistic huff-and-puff modes are proposed based on the peculiarity of the fault-block reservoir’s small oil-bearing area and broken geological structure. We establish three typical CO₂ synergistic huff-and-puff models and analyze the influence of different geological and development factors on the huff-and-puff performance with numerical simulation. Each factor’s sensitivity is clarified, and the enhanced oil recovery (EOR) mechanism of CO₂ synergistic huff and puff is proposed. The sensitivity evaluation results show that the reservoir rhythm, inter-well passage, well spacing, high-position well liquid production rate, and middle-well liquid production rate are extremely sensitive factors; the stratum dip and injection volume allocation scheme are sensitive factors; and the relationship with structural isobaths is insensitive. The EOR mechanism of synergistic huff and puff includes gravity differentiation, supplementary formation energy, CO₂ forming foam flooding, and coupling effect of production rate and oil reservoirs. The implementation conditions of the two-well cooperative stimulation mode are the simplest. The two-well model is suitable for thick oil layers with a positive rhythm and large formation dip. The single-well mode requires no channeling between the wells, and the multi-well mode requires multi-well rows and can control the intermediate well’s fluid production rate. Field application at C2X1 block shows a good performance with a total oil increment of 1280 t and an average water-cut reduction of 57.7%. Full article