4results about How to "Iterative convergence is fast" patented technology

The application provides a background velocity field reconstruction method and device based on reflected wave waveform inversion gradient preprocessing, a computer readable storage medium and an electronic device. The method comprises the following steps: based on near-offset information, inverse time migration is performed by calculating a Poynting vector, and a reflected wave field is obtained by reverse migration; the gradient of the velocity is calculated by using a reflected wave full waveform inversion technology based on an adaptive error function, the gradient of the velocity is preprocessed by using illumination energy compensation, the gradient of the preprocessed velocity is used to update the background velocity field, and a more accurate background velocity model is obtained. When the method is applied to model inversion, a more accurate background velocity model can be obtained, and the quality of a migration profile is significantly improved.

The application discloses a kind of AC / DC hybrid distribution network power flow calculation method and device considering incomplete LU decomposition preconditioning, and relates to the field of smart grid.The method comprises the following steps: establishing active / reactive control equation based on VSC steady-state equation;Based on Kirchhoff's current law, establish AC / DC node power imbalance equation;Taylor expansion is carried out on the above equation, and high-order terms are ignored, to obtain linearized unified power flow equation set and matrix form Jacobian matrix;Incomplete LU decomposition preconditioning is carried out on Jacobian matrix, and stable double-conjugate gradient method is used to solve, to obtain power flow solution.The application establishes unified linearized power flow model, combines incomplete LU decomposition preconditioning and stable double-conjugate gradient method, effectively reduces the sensitivity to initial value, improves the robustness and convergence speed of complex AC / DC hybrid system power flow calculation.

The present application relates to a kind of transmission line intelligent route selection method based on adaptive resolution grid and improved ant colony algorithm, comprising: after remote sensing image rasterization, adaptive quadtree image segmentation is carried out, and complete adaptive resolution grid map is obtained;Establish hierarchical analysis model, obtain the construction cost of each grid area in transmission line, i.e.grid cost, establish adaptive resolution grid map cost model;Through improved ant colony algorithm, the transmission line path after inflection point correction is obtained.The present application uses improved ant colony algorithm to speed up the iterative convergence of algorithm, and is combined with adaptive resolution grid, the reduction of grid number can significantly improve the efficiency of algorithm;The size of adaptive resolution grid changes according to the change of terrain on remote sensing map, can avoid the problem that the position accuracy of planned route is low;Inflection point correction is carried out to the planned route, reduces the number of corner tower that needs to be built, saves construction cost.

The present application relates to the technical field of deep learning, and particularly relates to a new device cold start method for smart home portrait construction, comprising dividing and processing historical record data sets of home devices to obtain input data sets; combining a label classification model and a meta learning model to perform meta training on a training task set to obtain an optimal initialization parameter group; generating a test task set from the input data set and performing meta testing based on the optimal initialization parameter group to obtain a label classification result; and performing cold start based on the label classification result, wherein the model of the present application can learn a group of initialization parameters with good universality from the historical data of other same kind of devices, and can quickly iterate and converge in the case of a small amount of data of a new device, thereby achieving good classification effect. The present application solves the problem that the use records of new devices cannot be correctly labeled and classified in the small sample scene when constructing a user portrait.