Worm gear machine
    1.
    发明授权

    公开(公告)号:US12145208B2

    公开(公告)日:2024-11-19

    申请号:US17471130

    申请日:2021-09-09

    Abstract: The present disclosure provides a worm gear machine, including a workbench, a cutter holder and a cutter holder adjusting system, where the cutter holder includes a big bracket, a first slide rail is disposed on the big bracket, a slide seat in sliding fit with the first slide rail is disposed on the first slide rail, a second slide rail is disposed on the slide seat, a small bracket in sliding fit with the second slide rail is disposed on the second slide rail; and a cutter holder spindle is disposed between the big bracket and the slide seat, a cutter bar synchronously rotating with the cutter holder spindle is disposed between an end of the cutter holder spindle facing toward the small bracket and the small bracket, and a gearbox for driving the cutter spindle to rotate is disposed in the big bracket.

    Method for constructing body-in-white spot welding deformation prediction model based on graph convolutional network

    公开(公告)号:US12093019B2

    公开(公告)日:2024-09-17

    申请号:US17830361

    申请日:2022-06-02

    CPC classification number: G05B19/4099 B23K31/003 G05B2219/49007

    Abstract: A method for constructing a body-in-white (BiW) spot welding deformation prediction model based on a graph convolutional network (GCN) includes: 1) acquiring a welding feature and 3D coordinates of a spot weld to form an eigenvector and extracting designed 3D coordinates at each 3D coordinate measurement point; 2) encoding, by an encoder, eigenvectors and designed 3D coordinate vectors into hidden space vectors of spot welds and hidden space vectors of the coordinate measurement points, respectively, and constructing a graph topology G through a k-nearest neighbors algorithm; 3) decomposing a Laplacian eigenvector of the constructed graph topology G to acquire frequency domain components, and linearly transforming eigenvalues corresponding to the frequency domain components to construct a multi-layer GCN; 4) inputting the thermodynamic and kinetic information of each coordinate measurement point into a deep neural network and decoding a final deformation at each coordinate measurement point; and 5) optimizing the model.

Patent Agency Ranking