Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

1860results about How to "Reduce limitations" patented technology

Super-dense edge computing network mobility management method based on deep reinforcement learning

The invention discloses a super-dense edge computing network mobility management method based on deep reinforcement learning. The super-dense edge computing network mobility management method includesthe steps: establishing a communication time delay model, a computing model, a QoS model and a service cost migration model according to environment information and processing resource information; establishing a mobile management model according to the established model information, simplifying the problem by adopting a dynamic loss queue technology and a Lyapunov optimization method, and abstractly describing a dynamic change process of an ultra-dense edge computing environment of the mobile management model by adopting a discrete time Markov decision process; and establishing an algorithmbased on deep reinforcement learning according to the abstract model and obtaining an optimal mobility management decision. According to the super-dense edge computing network mobility management method, for a super-dense edge computing network, the mobility management decision is small in limitation and good in mobility, and on the premise of considering the integrity, dynamics and balance of thesystem, the optimal decision of the association network and task allocation in the user moving process is realized.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Image object recognition method based on SURF

The invention provides an image object recognition method based on SURF (Speed Up Robust Feature), comprising the following steps: first, preprocessing images; second, extracting SURF corners and SURF descriptors of the images to describe the features of the images; third, processing the features through PCA data whitening and dimension reduction; establishing a bag-of-visual-words model through Kmeans clustering based on the features after processing, and using the bag-of-visual-words model to construct a visual vocabulary histogram of the images; and finally, carrying out training by a nonlinear support vector machine (SVM) classification method, and classifying the images to different categories. After classification model building of different images is completed in the training phase, the images tested in a concentrated way are detected in the testing phase, and therefore, different image objects can be recognized. The method has excellent performance in the aspects of recognition rate and speed, and can reflect the content of images more objectively and accurately. In addition, the classification result of an SVM classifier is optimized, and the error rate of judgment of the classifier and the limitation of the categories of training samples are reduced.
Owner:SHANGHAI JIAO TONG UNIV +1

Device and method for measuring three-phase permeability of supercritical CO2 emulsion by steady-state flow method

The invention relates to a device for measuring the three-phase permeability of supercritical CO2 emulsion by a steady-state flow method. The device comprises a one-dimensional rock core model and a computed tomography (CT) scanner, wherein an inlet end of the one-dimensional rock core model is connected an emulsion generator and a crude oil injection device which are connected with each other in parallel; an inlet end of the emulsion generator is connected with a CO2 gas injection device and a surface active agent injection device which are connected with each other in parallel; an outlet end of the one-dimensional rock core model is connected with a gas source bottle and a liquid-containing narrow-mouth bottle which are connected with each other in parallel; a gas outlet pipe of the liquid-containing narrow-mouth bottle is sequentially connected with a drying pipe and a flow meter. According to the method for measuring the three-phase permeability of the supercritical CO2 emulsion, the three-phase fluid saturation of the supercritical CO2 emulsion is accurately obtained by a CT double-energy synchronous scanning method, and the relevant data measured by the experiment is substituted into a Darcy-Weisbach formula, so that the three-phase relative permeability of the supercritical CO2 emulsion under the different degrees of saturation can be obtained; the method is also used for measuring CO2 foam flooding two-phase permeability. The device and the method are small in limitation, are capable of reasonably approaching the experimental real value, and are simple in operation and accurate in measurement.
Owner:CHINA UNIV OF PETROLEUM (EAST CHINA)

Video-based human body interaction action recognition method

The invention discloses a video-based human body interaction action recognition method which comprises the following steps of (S1) carrying out moving target detection on an inputted video frame imageby using an inter-frame difference method, (S2) carrying out feature extraction on a moving target obtained after processing, wherein the step (S2) includes the steps of (S21) extracting human body interaction action features on the moving target obtained after processing by using a mode of combining local space-time features and global optical flow features, (S22) describing optical flow and space-time interest points to form feature descriptors HOF and HOG, and (S23) passing the local space-time features and the global optical flow features through a BP neural network to obtain a probability matrix of an action class under a certain feature, (S3) giving different weights to probability matrixes obtained by using different features and carrying out weighted summation to obtain a fusion probability matrix, wherein an action class with the largest probability is an action class of a frame, and (S4) inputting an initial classification sequence into an improved normal distribution BP neural network to obtain final interaction action classification.
Owner:NORTH CHINA UNIVERSITY OF TECHNOLOGY

Online monitoring system and method of corrosion protection effect of oil well pipelines

The invention discloses an online monitoring system and method of a corrosion protection effect of oil well pipelines. The system comprises a remote control center (1), an in-situ online corrosion monitoring unit (2), a transmission optical fiber (3), a corrosion data collector (4), a sensor and a network cable (10), wherein the remote control center (1) is connected with the in-situ online corrosion monitoring unit (2), the in-situ online corrosion monitoring unit (2) is connected with the corrosion data collector (4) through the transmission optical fiber (3), and the corrosion data collector (4) is connected with the sensor through the network cable (10). The online monitoring system disclosed by the invention can determine the corrosion damage states of buried oil well pipelines, locate damage points of corrosion layers, and evaluate the aging state of corrosion protection layers to serve as the basis for formulating a maintenance scheme, and can determine the corrosion condition and rate of the oil well pipelines, predict the safe service lives of the oil well pipelines, can avoid potential hazards due to corrosion leakage, can optimize the optimum injection amount of a corrosion inhibitor and can evaluate the forced impressed current cathodic protection effect of the oil well pipelines.
Owner:BC P INC CHINA NAT PETROLEUM CORP +1

SAR image based on adversarial generation network, and visible light image mode conversion method

The invention relates to a SAR image based on adversarial generation network, and a visible light image mode conversion method. The method comprises: firstly, extracting feature vectors of satellite images at the same position, and enabling the feature vectors to serve as the prior information of the SAR image; And inputting the priori information and the SAR image into a generator to generate a visible light image with an SAR image target. Secondly, a discriminator in the generative adversarial network is trained, and a formula LGAN (GAB, D, A and B) = Eb-B [log D (b)] + Ea-A [log (1-D (GAB (a)))] is adopted as discrimination loss; And finally, judging whether the trained adversarial generation network has a model folding error or not, namely inputting different SAR images, and enabling most of the output of the generator to be the same visible light image. And meanwhile, another generator is trained, and the feature similarity of the two images is compared by adopting generation loss; generating a loss of LGAN (GAB, GBA, A, B) = Ea-A [| | GAB (GBA (a))- A||1]. And when network training is completed, curves of the judgment loss and the generation loss tend to be stable, the judgment loss is not increased any more, and the generation loss is not reduced any more.
Owner:AVIATION ARMY INST PEOPLES LIBERATION ARMY AIR FORCE RES INST +1
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products