TY - PAT
T1 - STEP file analysis-based vehicle body part characteristic information acquisition method
AU - Li, Tukun
AU - Kong, Chao
AU - Xu, Yuanping
AU - Zhang, Chaolong
AU - Fu, Hongsheng
AU - Cao, Yanlong
PY - 2023/10/13
Y1 - 2023/10/13
N2 - The invention discloses a vehicle body part characteristic information acquisition method based on STEP file analysis, which comprises the STEPs of acquiring a STEP file of a vehicle body part, and extracting boundary discrete points of edges based on parameter information of the edges in the STEP file; converting the functional surface into a NURBS curved surface, calculating and obtaining the value of boundary discrete points in a parameter domain by adopting a quasi-Newton method, then cutting the NURBS curved surface by adopting a ray method to obtain a surface point cloud, and converting the surface point cloud into an original space; acquiring local coordinates of the functional surface by adopting a principal component analysis method, and calculating the distance from each surface point cloud of the functional surface to the plane where the z-axis of the local coordinate system is located; determining the type of the functional surface and whether the two functional surfaces are vertical; and obtaining the functional surface type by adopting a naive Bayes classifier according to the boundary type, the surface type and the number of whether the functional surface and the adjacent surface are perpendicular and normal to the passing surface.
AB - The invention discloses a vehicle body part characteristic information acquisition method based on STEP file analysis, which comprises the STEPs of acquiring a STEP file of a vehicle body part, and extracting boundary discrete points of edges based on parameter information of the edges in the STEP file; converting the functional surface into a NURBS curved surface, calculating and obtaining the value of boundary discrete points in a parameter domain by adopting a quasi-Newton method, then cutting the NURBS curved surface by adopting a ray method to obtain a surface point cloud, and converting the surface point cloud into an original space; acquiring local coordinates of the functional surface by adopting a principal component analysis method, and calculating the distance from each surface point cloud of the functional surface to the plane where the z-axis of the local coordinate system is located; determining the type of the functional surface and whether the two functional surfaces are vertical; and obtaining the functional surface type by adopting a naive Bayes classifier according to the boundary type, the surface type and the number of whether the functional surface and the adjacent surface are perpendicular and normal to the passing surface.
KW - STEP
KW - functional surface
KW - vehicle body part
KW - NURBS curved surface
UR - https://patents.google.com/patent/CN116883685A/en?oq=CN116883685A
M3 - Patent
M1 - CN116883685A
Y2 - 2023/07/24
ER -