Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

4 results about "Rotation field" patented technology

Multi-modal information acquisition and roof global attitude monitoring method and system

The invention provides a multi-modal information acquisition and roof global attitude monitoring method and system, and relates to the technical field of mining safety monitoring and roadway surrounding rock control. The method comprises the following steps of: acquiring acoustic, optical, electrical and mine pressure multi-source data by arranging a fan-shaped drill hole, an annular electrode array and various mine pressure monitoring devices; a wave velocity profile, a fracture parameter set and a resistivity equivalent cloud picture are generated through wavelet noise reduction, fracture recognition and resistivity inversion, space-time registration with a mine pressure data sequence is carried out, and roof partition probability distribution is output through a space-time feature pyramid network. Furthermore, improved XGBoost is adopted for joint inversion of the thickness of the loose circle, the Poisson's ratio and the elastic modulus, probability distribution serves as a space weight, the separation amount and anchoring stress data are fused, and a roof displacement field, a curvature field and a rotation field are reconstructed. And finally, generating an early warning based on a preset safety threshold value, outputting a posture partition map and a monitoring report, and realizing top plate posture transparent deduction and support coordinated regulation and control.
Owner:陕西小保当矿业有限公司 +4

Rotary sound source identification and positioning method based on deep convolutional attention neural network

The invention discloses a rotating sound source recognition and positioning method based on a deep convolutional attention neural network, and belongs to the field of rotating sound source recognition, and the method comprises the steps: firstly carrying out the motion compensation and modal expansion of a sound pressure cross-spectrum matrix through a modal decomposition rotating beam forming algorithm, and generating a sound source distribution diagram in a rotating scene; then the sound source distribution map is input into a deep convolution attention neural network model, the model adopts an encoder-decoder structure, a channel and a space attention mechanism are fused, key sound source features are dynamically focused, noise interference is suppressed, and high-precision reconstruction of the sound source distribution map is achieved; and finally, carrying out local maximum value detection on a prediction map output by the network, and extracting a sound source space position. According to the method, the Doppler effect and phase distortion problems in rotating sound source positioning are effectively overcome, and the positioning precision, the anti-noise performance and the calculation efficiency in a complex rotating field are remarkably improved.
Owner:ANHUI UNIV

A structure deformation reconstruction method and system based on a four-node inverse plate shell element containing a drilling degree of freedom

The present application belongs to the field of structural deformation reconstruction, and specifically discloses a structural deformation reconstruction method and system based on a four-node inverse plate shell element containing a drilling degree of freedom, comprising: discretizing the structure into a plurality of four-node inverse plate shell elements, and constructing a shear strain matrix by using a discrete shear gap method; kinematically constraining the drilling degree of freedom by using a continuum mechanics rotation field, solving the continuum medium rotation by deriving the global coordinate system from the natural coordinate system shape function, and supplementing the sixth degree of freedom of the element around the normal line; deriving a coordinate transformation matrix based on the assigned sixth degree of freedom, introducing a node coordinate system, transforming the element stiffness matrix to the node coordinate system, and then transforming it to the global coordinate system; and finally, incorporating the above construction method into the least squares functional framework, assembling the global inverse finite element equation by minimizing the error between the theoretical strain and the measured strain, and reconstructing the full-field displacement of the structure. The present application can realize high-precision deformation reconstruction of complex stiffened plate shells and large-curvature structures.
Owner:HUAZHONG UNIV OF SCI & TECH

Layered slicing method and device for laser metal deposition based on rotation driving deformation and direction field collaborative optimization

The application discloses a kind of based on rotation driving deformation and direction field collaborative optimization laser metal deposition layering slicing method and equipment, three major manufacturing targets, such as support-free, strength enhancement and surface quality, are converted into the geometric constraint of local deposition direction of each point in model interior, and it is not directly to find messy direction, but a smooth quaternion rotation field is calculated for the whole model, and the optimization target is to find a virtual rotation deformation, so that when the model is deformed according to the field, it can be printed only with a fixed global direction (such as the vertical Z axis), and everywhere meets the constraint conditions such as support-free, then, the height information of the deformed model is mapped back to the original shape, forming a scalar field, and the isosurface of the scalar field is the final curved surface processing layer. The optimized rotation field ensures that the generated curved surface layer is not only geometrically optimal, but also can be directly and safely used for actual multi-axis machining, with more stable structure and higher precision.
Owner:NANJING NORMAL UNIVERSITY