Patents
Literature

3571results about How to "High precision" patented technology

Method for forecasting short-term power in wind power station

InactiveCN102102626AHigh precision
The invention belongs to the technical field of electric power system forecasting and controlling, in particular relating to a method for forecasting short-term power in a wind power station. The method comprises the following steps: firstly, acquiring actual measured wind speed and power data, and processing the acquired data by adopting a differential autoregressive moving average model and a power forecasting model based on the combination of wavelet transformation and a neural network, thus obtaining a super short-term forecasting power; then acquiring the wind speed, wind direction, air temperature, humidity and atmosphere pressure data of different heights, processing the acquired data by adopting a BP (back propagation) neural network, a self-adaptive fuzzy neural inference system model and a least square support vector machine model through a power combination forecasting method based on a maximal information entropy principle, thus obtaining short-term forecast power; and finally processing the super short-term forecast power, the average error of the super short-term forecast power, the short-term forecast power and the average error of the short-term forecast power which are utilized as input by a combination forecasting method based on the BP neural network, thus obtaining the final short-term forecast power. According to the invention, the accuracy of forecasting power in 72 hours in the future in the wind power station is improved, and a reference is provided for the resonable dispatch of a power grid.
Owner:NORTH CHINA ELECTRIC POWER UNIV (BAODING) +1

Precise positionable and compensable heavy-load mechanical arm

The invention discloses a precise positionable and compensable heavy-load mechanical arm which comprises a power device, a base, an arm assembly, a wrist assembly, a flexible claw and an automatic control system. The arm assembly comprises a lower arm assembly, a middle arm assembly and an upper arm assembly. The precise positionable and compensable heavy-load mechanical arm can adapt to a heavy-load working environment in a hydraulic drive mode, and on the basis, an external control system sends an instruction to an electric spindle according to information fed back by external and internal sensors and the like, so that a first connecting rod mechanism and a second connecting rod mechanism which are in transmission connection with the electric spindle perform fine adjustment compensation on the aspects of distance, angle and the like of the mechanical arm, and the precise effect can be achieved. When the mechanical arm is used, various sensor and computer control technologies are combined, so that working state monitoring can be achieved in the working process of the mechanical arm, precise mechanical arm operation can be ensured, meanwhile transmission errors of a transmission chain are decreased by using the electric spindle and other matched parts, the transmission accuracy is improved, and precise motion and safety guarantee of the wrist and the flexible claw is achieved.
Owner:CHONGQING JIAOTONG UNIVERSITY

High-fineness urban three-dimensional modeling method

The invention discloses a high-fineness urban three-dimensional modeling method and relates to the field of three-dimensional digital urban construction, airborne LIDAR (light detection and ranging) is adopted for acquiring original aerial survey data result, and an urban high-precision digital elevation model, a digital orthophoto map and a building three-dimensional body frame model are manufactured on the basis, thereby forming a foundation framework of an urban three-dimensional scene; then a vehicle-mounted movable laser scanning device is used for acquiring vehicle-mounted movable laser scanning original data result, and a high-fineness model of all types of opuscules and ground objects of an urban is acquired by performing the ground object high-fineness three-dimensional modeling under the mode of fusing vehicle-mounted point cloud after precision optimization with a photo according to a ground object parameter model base under the three-dimensional modeling environment; and the foundation framework of the urban three-dimensional scene and the high-fineness model of all the types of the opuscules and the ground objects of the urban are integrated, thereby acquiring a high-fineness three-dimensional virtual urban scene of the urban. With the adoption of the method, production efficiency is improved, project cost is reduced, development cycle is shortened, modeling fineness is improved, and actual application needs can be met.
Owner:星际空间(天津)科技发展有限公司

Automatic monitoring apparatus and method for layered vertical sedimentation and lateral displacement of roadbed

The invention discloses a road foundation layered vertical settlement and transversal displacement automatic monitoring device and a monitoring method thereof in the technical field of optical measurement. The invention adopts a technical proposal that the automatic monitoring device comprises a measuring and positioning unit, a laser displacement sensing unit, a laser angle sensing unit, a measuring signal control unit, a measuring data transmission unit, a central processing unit and a power module; and the automatic monitoring method comprises: firstly, assembling various devices; secondly, starting a pulling device, stopping the device when a positioning sensor arrives at a position of a magnetic ring, measuring displacement data and angle data, and transmitting the data to the central processing unit for storage; thirdly, restarting the pulling device, and repeatedly measuring and saving the data until a measuring tube contacts a limit switch; and processing all the data of the central processing unit, and obtaining road foundation vertical settlement and transversal displacement parameters. The automatic monitoring device and the automatic monitoring method apply laser measurement technology, improve the measurement precision and the measurement depth, and simultaneously realize remote automatic monitoring.
Owner:BEIJING JIAOTONG UNIV

Semantic image segmentation method and system based on edge enhancement

ActiveCN111462126Aaccurate segmentationHigh precision
The invention provides a semantic image segmentation method and system based on edge enhancement. The method comprises the steps of preprocessing an input image; establishing an edge enhancement network model, wherein the edge enhancement network model comprises a lightweight edge network and a deep semantic network; inputting the preprocessed image into a lightweight edge network, and adaptivelypaying attention to local edge information of the image by utilizing a spatial attention module; inputting the preprocessed images into a deep semantic network in batches, and optimizing the output ofthe deep network at different stages by using a channel attention module; carrying out cascading dimensionality reduction on the obtained features, fusing feature information of different levels, andadopting a channel attention module to perform optimization; performing normalizing to obtain an image segmentation result predicted by the edge enhancement network model; and calculating cross entropy loss and focus loss of the predicted segmentation image and a given standard segmentation image so as to respectively supervise output of the lightweight edge network and the deep semantic network,and updating model parameters of the edge enhancement network by using a random gradient descent method so as to realize accurate segmentation of an input image.
Owner:WUHAN UNIV
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