Summary Plug-and-perforation (P-n-P) completion has been widely used in horizontal wells for the development of unconventional reservoirs. In field, uneven proppant distribution among different fractures within a fracturing stage frequently observed P-n-P treatments, leaving large portion reservoir volume understimulated. this paper, an efficient 3D multiphase particle-in-cell (MP-PIC) method to simulate transport multiple (fracture near heel, middle fracture, fracture toe) at field scale....

In an open‐pit mine slope, rock mass has multiple joint structures and blasting operations have obvious influence on its stability. Therefore, accurately predicting the vibration is necessary to ensure slope this study, signals monitored at a site with different masses were used investigate attenuation characteristics of through peak particle velocity (PPV), frequency characteristics, energy distribution analyzed time‐frequency processing method. The results demonstrated that main dolomite...

With the diversification and complexity of higher education, methods student management in universities are continuously evolving. Achieving an effective balance between humanized institutionalized is important issue currently faced university management. Humanized centers on students, focusing their individual development psychological needs; whereas emphasizes norms, standards, enforceability to ensure fairness order. This paper aims explore practices management, analyze challenges they...

Accurate remaining useful life (RUL) prediction is of great significance to the safe operation aircraft. Graph neural network (GNN) can describe spatial structure relationship between variables, which provides a new solution problem RUL prediction. In this paper, we propose method based on GNN, named Comprehensive Dynamic Structure Neural Network (CDSG). The proposed CDSG not only fully exploits health information hidden in condition monitoring data, but also takes into account structural...

Summary The use of hydraulic fracturing has taken off over the past decade, and importance efficient proppant placement in fractures increased accordingly. Connection with weak-formation bedding planes brings about distinctive fracture propagation development. This might hinder from extending a vertical direction, yet they instead propagate horizontal direction after existing planes. plane introduces additional hydrocarbon flow path during recovery process. naturally leads to proppants...

Fault diagnosis is an important technology to ensure the safe and reliable operation of equipment. Deep learning driven by big data brings new opportunities for fault diagnosis. Due diversity complexity actual distribution, a algorithm based on non-negative sparse constrained deep neural networks (NSCDNN) Dempster-Shafer theory (DST) proposed in this paper. The network trained constraint constraint, which can learn part-based representation data. improved DST combined with classification...

Groundwater is an important water resource, and groundwater level (GWL) forecasting a useful tool for supporting the sustainable management of resources. Existing studies have shown that GWLs can be accurately predicted by combining artificial neural network model with meteorological hydrological factors. However, GWL data are typically geographic spatiotemporal series data, current considered only spatial distance factor when predicting GWLs. In karst aquifers, affected developmental degree...

In this paper, a new framework for construction of Cardan grille information hiding is proposed. Based on the semantic image inpainting technique, stego are driven by secret messages directly. A mask called Digital Grille (DCG) determining hidden location introduced to hide message. The message written corrupted region that needs be filled in advance. Then with fed into Generative Adversarial Network (GAN) completion. adversarial game not only reconstruct image, but also generate which...

Automatic medical image classification is difficult because of the lacking training data. As manual labeling too costly, we provide an automatic solution to this problem by making use radiology report associated with images. We first segment and reconstruct 3D regions interest (ROIs) from images, extract pathology anatomy information report. anatomical atlas map ROIs part(s) match same text. In way, are automatically labeled types which can be served as class labels, a data set large number...

Based on the characteristics of shield tunnel structure and marine environment, this paper discusses durability factors affecting joint components tunnel. engineering practices study draws conclusions as follows: tidal water pressure causes increase decrease compression displacement rubber gasket, reduces its fatigue lifetime; impermeability gasket is antagonistic to lifetime in condition high pressure, should coordinate with service life when meets requirements waterproof performance;...

Collaborative filtering (CF) is one of the most successful techniques in recommender systems. By utilizing co-rated items pairwise users for similarity measurements, traditional CF uses a weighted summation to predict unknown ratings based on available ones. However, practice, rating matrix too sparse find sufficiently many items, thus leading inaccurate predictions. To address case data, we propose an iterative that updates and matrix. The improved incrementally selects reliable subsets...

In this paper, we conduct research on the applications of multimedia auxiliary teaching system with computer to education clinical medicine.Clinical medical and other related disciplines both identity particularity it is not just teach traditional theory principle.More need understand modern development latest medicine.Our provides novel paradigm assisted mechanism which will be meaningful.

Aiming at the problem in prediction of nuclear power working condition parameter, this paper uses a large number time series collected by plant sensor detection system to propose multi-feature fusion multi-step state model based on long short-term memory network (LSTM). This takes SG1 steam pressure data real-time parameter plants as research object. Firstly, is preprocessed for problems missing and inconsistent sampling scales, then structural design modeling completed LSTM. Finally,...

Abstract. Evaluating, ranking, and clustering (ERC) stand as fundamental tasks in scientific research, each requiring a mathematical foundation. This study presents an ERC system anchored the CCHZ-DISO (Chen, Chen, Hu, Zhou-Distance between Indices of Simulation Observation) system. Previous research underscores optimality achieved by (Hu et al., 2022). Since inception CCHZ- DISO-series Hu al. (2019), DISO has found extensive applications across various domains including geography,...

Optical Coherence Tomography Angiography (OCTA) is a crucial imaging technique for visualizing retinal vasculature and diagnosing eye diseases such as diabetic retinopathy glaucoma. However, precise segmentation of OCTA remains challenging due to the multi-scale vessel structures noise from poor image quality lesions. In this study, we proposed OCTAMamba, novel U-shaped network based on Mamba architecture, designed segment in accurately. OCTAMamba integrates Quad Stream Efficient Mining...

Along with the reform of times, people hold different pursuits and aesthetic views about clothing, naturally their understanding clothing is different.Teachers must always be a good model virtue for students.There no exception to appearance, because teacher addressed appropriately tastefully accompanied by graceful manner genial language.In general, promotion moral education students influenced every word action teacher.The teaching effect prestige can better improved, if his or her...

To improve the performance of deep neural networks, Mixup method has been proposed to alleviate their memorization issues and sensitivity adversarial samples. This provides networks with better generalization abilities. The learning principle is essentially train for regularization tasks a convex combination original feature vectors labels. However, soft labels are generated directly using mixing ratio without dealing uncertain information during process. Therefore, this paper proposes new...