Abstract: A consensus graph learning-based multi-view clustering method includes: S11, inputting an original data matrix to obtain a spectral embedding matrix; S12, calculating a similarity graph matrix and a Laplacian matrix based on the spectral embedding matrix; S13, applying spectral clustering to the calculated similarity graph matrix to obtain spectral embedding representations; S14, stacking inner products of the normalized spectral embedding representations into a third-order tensor and using low-rank tensor representation learning to obtain a consistent distance matrix; S15, integrating spectral embedding representation learning and low-rank tensor representation learning into a unified learning framework to obtain a objective function; S16, solving the obtained objective function through an alternative iterative optimization strategy; S17, constructing a consistent similarity graph based on the solved result; and S18, applying spectral clustering to the consistent similarity graph to obtain a clustering resul

Abstract: An unsupervised feature selection method based on latent space learning and manifold constraints includes: S11, inputting an original data matrix to obtain a feature selection model; S12, embedding latent space learning into the feature selection model to obtain a feature selection model with the latent space learning; S13, adding a graph Laplacian regularization term into the feature selection model with the latent space learning to obtain an objective function; S14, solving the objective function by adopting an alternative iterative optimization strategy; and S15, sequencing each feature in the original matrix, and selecting the first k features to obtain an optimal feature subset. Feature selection is performed in a learned potential latent space, and the space is robust to noise. The potential latent space is modeled by non-negative matrix decomposition of a similarity matrix, and the matrix decomposition can unambiguously reflect relationships between data instances.

Abstract: A method for coupling hydraulic fracture network extension and production performance of a horizontal well in an unconventional oil and gas reservoir includes: establishing a complex hydraulic fracture network model of a fractured horizontal well in an unconventional oil and gas reservoir based on a fracture extension theory; constructing three-dimensional three-phase mathematical models of seepage for the fractured horizontal well based on an embedded discrete fracture model; and constructing a fully implicit numerical calculation model by a finite difference method through three-dimensional orthogonal grids, and solving iteratively, thereby accurately predicting a production performance characteristic of the fractured horizontal well in the unconventional oil and gas reservoir.

Abstract: The invention discloses a natural gas diffusion coefficient measurement auxiliary device based on a hand-operated lifting device, comprising a core chamber, a bracket, a core preservation device, and a hand-operated lifting device; the left side of the core chamber is connected with a methane measuring chamber, and the right side of the core chamber is connected with a nitrogen measuring chamber; a rotatable bracket is installed on the lower left side of the core chamber, and the lower right side of the core chamber is connected with the hand-operated lifting device; the core chamber is rotated by the hand-operated lifting device with the support as the center; a horizontal platform at the lower part of the core chamber is provided with a revolving door that can accommodate the left end of the core chamber; a core preservation device is installed at the lower part of the revolving door.

Abstract: An experimental device for carbon dioxide imbition, diffusion and oil discharge in a tight oil reservoir includes: a multistage rock core holder connected with a confining pressure pump and including a pair of connecting holes arranged at an upper end and a lower end thereof with an oil filler pipe connecting therebetween, a crude oil injection device and a recovery device respectively connected to the upper and lower ends, an intermediate container connected to both a high-pressure cylinder and an injection pump, a return pressure pump, a collection device and a control system. A plurality of rows of openings is arranged at a side of the multistage rock core holder to act as a gas inlet connected with the intermediate container via a pipeline, and a gas outlet connected with the recovery device; heating layers are arranged at inner walls of the multistage rock core holder and the intermediate container.